Training in progress, step 3000, checkpoint
Browse files- checkpoint-3000/config.json +47 -0
- checkpoint-3000/generation_config.json +10 -0
- checkpoint-3000/model.safetensors +3 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/trainer_state.json +462 -0
- checkpoint-3000/training_args.bin +3 -0
checkpoint-3000/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2048,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention"
|
| 28 |
+
],
|
| 29 |
+
"max_position_embeddings": 2048,
|
| 30 |
+
"max_window_layers": 28,
|
| 31 |
+
"model_type": "qwen3",
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_hidden_layers": 12,
|
| 34 |
+
"num_key_value_heads": 4,
|
| 35 |
+
"pad_token_id": 1,
|
| 36 |
+
"rms_norm_eps": 1e-06,
|
| 37 |
+
"rope_parameters": {
|
| 38 |
+
"rope_theta": 10000,
|
| 39 |
+
"rope_type": "default"
|
| 40 |
+
},
|
| 41 |
+
"sliding_window": null,
|
| 42 |
+
"tie_word_embeddings": true,
|
| 43 |
+
"transformers_version": "5.14.1",
|
| 44 |
+
"use_cache": false,
|
| 45 |
+
"use_sliding_window": false,
|
| 46 |
+
"vocab_size": 32768
|
| 47 |
+
}
|
checkpoint-3000/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "5.14.1",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
checkpoint-3000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:864d77d0bf42c1ae4a9240b51ec1f36f67213f46d284d955641840801de88584
|
| 3 |
+
size 402750928
|
checkpoint-3000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0341a268490231afbed89dd7211842fede3e849f3766f0a273e84d8860fc029e
|
| 3 |
+
size 805587275
|
checkpoint-3000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ffffd41cb5466a23271a8c6303a885c8e75cf7a03496c0a7cb7f448827155d8
|
| 3 |
+
size 14645
|
checkpoint-3000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e57a1575568428ec18360ecc95e054ed4691dffa86343f7cfd5491befb07e30a
|
| 3 |
+
size 1465
|
checkpoint-3000/trainer_state.json
ADDED
|
@@ -0,0 +1,462 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.026214395526076496,
|
| 6 |
+
"eval_steps": 3000,
|
| 7 |
+
"global_step": 3000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00043690659210127495,
|
| 14 |
+
"grad_norm": 1.8826903104782104,
|
| 15 |
+
"learning_rate": 2.4500000000000003e-05,
|
| 16 |
+
"loss": 9.762939453125,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0008738131842025499,
|
| 21 |
+
"grad_norm": 0.9995923042297363,
|
| 22 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 23 |
+
"loss": 8.305597534179688,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.001310719776303825,
|
| 28 |
+
"grad_norm": 0.9061496257781982,
|
| 29 |
+
"learning_rate": 7.45e-05,
|
| 30 |
+
"loss": 7.173495483398438,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0017476263684050998,
|
| 35 |
+
"grad_norm": 1.6024847030639648,
|
| 36 |
+
"learning_rate": 9.95e-05,
|
| 37 |
+
"loss": 6.624603271484375,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.002184532960506375,
|
| 42 |
+
"grad_norm": 1.2123334407806396,
|
| 43 |
+
"learning_rate": 0.0001245,
|
| 44 |
+
"loss": 6.243399658203125,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.00262143955260765,
|
| 49 |
+
"grad_norm": 1.0432322025299072,
|
| 50 |
+
"learning_rate": 0.0001495,
|
| 51 |
+
"loss": 5.9879296875,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0030583461447089245,
|
| 56 |
+
"grad_norm": 0.9280146360397339,
|
| 57 |
+
"learning_rate": 0.00017449999999999999,
|
| 58 |
+
"loss": 5.776607666015625,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0034952527368101996,
|
| 63 |
+
"grad_norm": 1.0289900302886963,
|
| 64 |
+
"learning_rate": 0.00019950000000000002,
|
| 65 |
+
"loss": 5.5920703125,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.003932159328911475,
|
| 70 |
+
"grad_norm": 1.0593407154083252,
|
| 71 |
+
"learning_rate": 0.0002245,
|
| 72 |
+
"loss": 5.437271728515625,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.00436906592101275,
|
| 77 |
+
"grad_norm": 1.0122662782669067,
|
| 78 |
+
"learning_rate": 0.0002495,
|
| 79 |
+
"loss": 5.287777709960937,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.004805972513114025,
|
| 84 |
+
"grad_norm": 0.7662743926048279,
|
| 85 |
+
"learning_rate": 0.0002745,
|
| 86 |
+
"loss": 5.155453491210937,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0052428791052153,
|
| 91 |
+
"grad_norm": 0.7941539287567139,
|
| 92 |
+
"learning_rate": 0.0002995,
|
| 93 |
+
"loss": 5.030631713867187,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.005679785697316574,
|
| 98 |
+
"grad_norm": 0.6195730566978455,
|
| 99 |
+
"learning_rate": 0.00032450000000000003,
|
| 100 |
+
"loss": 4.909389953613282,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.006116692289417849,
|
| 105 |
+
"grad_norm": 0.6587674617767334,
|
| 106 |
+
"learning_rate": 0.0003495,
|
| 107 |
+
"loss": 4.786273498535156,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.006553598881519124,
|
| 112 |
+
"grad_norm": 0.7233771681785583,
|
| 113 |
+
"learning_rate": 0.0003745,
|
| 114 |
+
"loss": 4.6648342895507815,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.006990505473620399,
|
| 119 |
+
"grad_norm": 0.5489601492881775,
|
| 120 |
+
"learning_rate": 0.0003995,
|
| 121 |
+
"loss": 4.555048522949218,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.007427412065721674,
|
| 126 |
+
"grad_norm": 0.6154086589813232,
|
| 127 |
+
"learning_rate": 0.0004245,
|
| 128 |
+
"loss": 4.461051330566407,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.00786431865782295,
|
| 133 |
+
"grad_norm": 0.41333407163619995,
|
| 134 |
+
"learning_rate": 0.00044950000000000003,
|
| 135 |
+
"loss": 4.374936828613281,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.008301225249924224,
|
| 140 |
+
"grad_norm": 0.5036063194274902,
|
| 141 |
+
"learning_rate": 0.0004745,
|
| 142 |
+
"loss": 4.3033209228515625,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.0087381318420255,
|
| 147 |
+
"grad_norm": 0.3687891364097595,
|
| 148 |
+
"learning_rate": 0.0004995,
|
| 149 |
+
"loss": 4.233715209960938,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.009175038434126774,
|
| 154 |
+
"grad_norm": 0.5433846116065979,
|
| 155 |
+
"learning_rate": 0.0005245,
|
| 156 |
+
"loss": 4.186253967285157,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.00961194502622805,
|
| 161 |
+
"grad_norm": 0.439351350069046,
|
| 162 |
+
"learning_rate": 0.0005495,
|
| 163 |
+
"loss": 4.139383850097656,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.010048851618329325,
|
| 168 |
+
"grad_norm": 0.36215880513191223,
|
| 169 |
+
"learning_rate": 0.0005745,
|
| 170 |
+
"loss": 4.08899658203125,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.0104857582104306,
|
| 175 |
+
"grad_norm": 0.3970701992511749,
|
| 176 |
+
"learning_rate": 0.0005995000000000001,
|
| 177 |
+
"loss": 4.061238403320313,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.010922664802531873,
|
| 182 |
+
"grad_norm": 0.3410918712615967,
|
| 183 |
+
"learning_rate": 0.0006245000000000001,
|
| 184 |
+
"loss": 4.026336669921875,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.011359571394633148,
|
| 189 |
+
"grad_norm": 0.3047930598258972,
|
| 190 |
+
"learning_rate": 0.0006495,
|
| 191 |
+
"loss": 3.9928851318359375,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.011796477986734423,
|
| 196 |
+
"grad_norm": 0.2819700241088867,
|
| 197 |
+
"learning_rate": 0.0006745,
|
| 198 |
+
"loss": 3.9584146118164063,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.012233384578835698,
|
| 203 |
+
"grad_norm": 0.29095014929771423,
|
| 204 |
+
"learning_rate": 0.0006995,
|
| 205 |
+
"loss": 3.9291363525390626,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.012670291170936973,
|
| 210 |
+
"grad_norm": 0.2987957298755646,
|
| 211 |
+
"learning_rate": 0.0007245000000000001,
|
| 212 |
+
"loss": 3.9090225219726564,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.013107197763038248,
|
| 217 |
+
"grad_norm": 0.28419050574302673,
|
| 218 |
+
"learning_rate": 0.0007495000000000001,
|
| 219 |
+
"loss": 3.890744934082031,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.013544104355139523,
|
| 224 |
+
"grad_norm": 0.3039053976535797,
|
| 225 |
+
"learning_rate": 0.0007745,
|
| 226 |
+
"loss": 3.861073303222656,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.013981010947240798,
|
| 231 |
+
"grad_norm": 0.25676754117012024,
|
| 232 |
+
"learning_rate": 0.0007995,
|
| 233 |
+
"loss": 3.8428253173828124,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.014417917539342073,
|
| 238 |
+
"grad_norm": 0.2573896646499634,
|
| 239 |
+
"learning_rate": 0.0008245,
|
| 240 |
+
"loss": 3.8260653686523436,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.014854824131443348,
|
| 245 |
+
"grad_norm": 0.272127240896225,
|
| 246 |
+
"learning_rate": 0.0008495000000000001,
|
| 247 |
+
"loss": 3.8006341552734373,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.015291730723544623,
|
| 252 |
+
"grad_norm": 0.23205944895744324,
|
| 253 |
+
"learning_rate": 0.0008745000000000001,
|
| 254 |
+
"loss": 3.7862649536132813,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.0157286373156459,
|
| 259 |
+
"grad_norm": 0.22847425937652588,
|
| 260 |
+
"learning_rate": 0.0008995,
|
| 261 |
+
"loss": 3.771934814453125,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.016165543907747174,
|
| 266 |
+
"grad_norm": 0.2651786208152771,
|
| 267 |
+
"learning_rate": 0.0009245,
|
| 268 |
+
"loss": 3.76009521484375,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.01660245049984845,
|
| 273 |
+
"grad_norm": 0.24903950095176697,
|
| 274 |
+
"learning_rate": 0.0009495,
|
| 275 |
+
"loss": 3.7454238891601563,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.017039357091949724,
|
| 280 |
+
"grad_norm": 0.24524764716625214,
|
| 281 |
+
"learning_rate": 0.0009745000000000001,
|
| 282 |
+
"loss": 3.735928955078125,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.017476263684051,
|
| 287 |
+
"grad_norm": 0.22325558960437775,
|
| 288 |
+
"learning_rate": 0.0009995000000000002,
|
| 289 |
+
"loss": 3.7209417724609377,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.017913170276152274,
|
| 294 |
+
"grad_norm": 0.23860357701778412,
|
| 295 |
+
"learning_rate": 0.001,
|
| 296 |
+
"loss": 3.7122769165039062,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.01835007686825355,
|
| 301 |
+
"grad_norm": 0.2162218689918518,
|
| 302 |
+
"learning_rate": 0.001,
|
| 303 |
+
"loss": 3.690401611328125,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.018786983460354824,
|
| 308 |
+
"grad_norm": 0.2171812504529953,
|
| 309 |
+
"learning_rate": 0.001,
|
| 310 |
+
"loss": 3.6825027465820312,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.0192238900524561,
|
| 315 |
+
"grad_norm": 0.22677843272686005,
|
| 316 |
+
"learning_rate": 0.001,
|
| 317 |
+
"loss": 3.6679034423828125,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.019660796644557374,
|
| 322 |
+
"grad_norm": 0.23934350907802582,
|
| 323 |
+
"learning_rate": 0.001,
|
| 324 |
+
"loss": 3.6494000244140623,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.02009770323665865,
|
| 329 |
+
"grad_norm": 0.20819289982318878,
|
| 330 |
+
"learning_rate": 0.001,
|
| 331 |
+
"loss": 3.640907897949219,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.020534609828759924,
|
| 336 |
+
"grad_norm": 0.22890810668468475,
|
| 337 |
+
"learning_rate": 0.001,
|
| 338 |
+
"loss": 3.6309326171875,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.0209715164208612,
|
| 343 |
+
"grad_norm": 0.2085026353597641,
|
| 344 |
+
"learning_rate": 0.001,
|
| 345 |
+
"loss": 3.6261746215820314,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.021408423012962474,
|
| 350 |
+
"grad_norm": 0.22136099636554718,
|
| 351 |
+
"learning_rate": 0.001,
|
| 352 |
+
"loss": 3.614878845214844,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.021845329605063746,
|
| 357 |
+
"grad_norm": 0.21210630238056183,
|
| 358 |
+
"learning_rate": 0.001,
|
| 359 |
+
"loss": 3.599817810058594,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.02228223619716502,
|
| 364 |
+
"grad_norm": 0.24638274312019348,
|
| 365 |
+
"learning_rate": 0.001,
|
| 366 |
+
"loss": 3.591536865234375,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.022719142789266296,
|
| 371 |
+
"grad_norm": 0.20501184463500977,
|
| 372 |
+
"learning_rate": 0.001,
|
| 373 |
+
"loss": 3.58053955078125,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.02315604938136757,
|
| 378 |
+
"grad_norm": 0.2101815640926361,
|
| 379 |
+
"learning_rate": 0.001,
|
| 380 |
+
"loss": 3.5824459838867186,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.023592955973468846,
|
| 385 |
+
"grad_norm": 0.22906431555747986,
|
| 386 |
+
"learning_rate": 0.001,
|
| 387 |
+
"loss": 3.564821472167969,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.02402986256557012,
|
| 392 |
+
"grad_norm": 0.20708167552947998,
|
| 393 |
+
"learning_rate": 0.001,
|
| 394 |
+
"loss": 3.5566305541992187,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.024466769157671396,
|
| 399 |
+
"grad_norm": 0.21956811845302582,
|
| 400 |
+
"learning_rate": 0.001,
|
| 401 |
+
"loss": 3.5507748413085936,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.02490367574977267,
|
| 406 |
+
"grad_norm": 0.24124488234519958,
|
| 407 |
+
"learning_rate": 0.001,
|
| 408 |
+
"loss": 3.5426095581054686,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.025340582341873946,
|
| 413 |
+
"grad_norm": 0.20921742916107178,
|
| 414 |
+
"learning_rate": 0.001,
|
| 415 |
+
"loss": 3.531602783203125,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.02577748893397522,
|
| 420 |
+
"grad_norm": 0.19601280987262726,
|
| 421 |
+
"learning_rate": 0.001,
|
| 422 |
+
"loss": 3.5225894165039064,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.026214395526076496,
|
| 427 |
+
"grad_norm": 0.20243392884731293,
|
| 428 |
+
"learning_rate": 0.001,
|
| 429 |
+
"loss": 3.5183840942382814,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.026214395526076496,
|
| 434 |
+
"eval_loss": 3.518667221069336,
|
| 435 |
+
"eval_runtime": 5.8945,
|
| 436 |
+
"eval_samples_per_second": 165.579,
|
| 437 |
+
"eval_steps_per_second": 10.349,
|
| 438 |
+
"step": 3000
|
| 439 |
+
}
|
| 440 |
+
],
|
| 441 |
+
"logging_steps": 50,
|
| 442 |
+
"max_steps": 114440,
|
| 443 |
+
"num_input_tokens_seen": 0,
|
| 444 |
+
"num_train_epochs": 1,
|
| 445 |
+
"save_steps": 3000,
|
| 446 |
+
"stateful_callbacks": {
|
| 447 |
+
"TrainerControl": {
|
| 448 |
+
"args": {
|
| 449 |
+
"should_epoch_stop": false,
|
| 450 |
+
"should_evaluate": false,
|
| 451 |
+
"should_log": false,
|
| 452 |
+
"should_save": true,
|
| 453 |
+
"should_training_stop": false
|
| 454 |
+
},
|
| 455 |
+
"attributes": {}
|
| 456 |
+
}
|
| 457 |
+
},
|
| 458 |
+
"total_flos": 3.56339612123136e+17,
|
| 459 |
+
"train_batch_size": 16,
|
| 460 |
+
"trial_name": null,
|
| 461 |
+
"trial_params": null
|
| 462 |
+
}
|
checkpoint-3000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b89574d4fb532cbff16922a1304201180637df9c21820d655203050012091374
|
| 3 |
+
size 5329
|