Training in progress, step 4000, checkpoint

checkpoint-4000/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 30000
+}

checkpoint-4000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e8f85f934a700880e3a50d73a83904e1c2ea87aa6a9651837239096edf71a3
+size 435544704

checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816dee7d0d4e05601a49b92272b674c44e2dab9623f8d3b9fb9dd49e6f0e3da1
+size 871183627

checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e47ddef9c1303c7e2cbdd472ca97d5509b3e46d8270e5e0745a562d873b4f23e
+size 14709

checkpoint-4000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0033c7745b46bdca3ecab5787678834ca68f7f7e1288869dceeb38812abc253
+size 1383

checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b02c8501d174134379a065836023b6fa228ce45fa2d445b6c2761cd0f566c1
+size 1465

checkpoint-4000/special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

checkpoint-4000/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-4000/trainer_state.json

@@ -0,0 +1,191 @@
+{
+  "best_global_step": 3920,
+  "best_metric": 5.1533684730529785,
+  "best_model_checkpoint": null,
+  "epoch": 10.204081632653061,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002551020408163265,
+      "grad_norm": 15.784777641296387,
+      "learning_rate": 0.0,
+      "loss": 10.3373,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0758121013641357,
+      "learning_rate": 7.82e-05,
+      "loss": 6.9019,
+      "step": 392
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.932833671569824,
+      "eval_runtime": 19.4192,
+      "eval_samples_per_second": 1298.248,
+      "eval_steps_per_second": 5.098,
+      "step": 392
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8500937223434448,
+      "learning_rate": 9.613387978142077e-05,
+      "loss": 5.6855,
+      "step": 784
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.585794448852539,
+      "eval_runtime": 19.3584,
+      "eval_samples_per_second": 1302.326,
+      "eval_steps_per_second": 5.114,
+      "step": 784
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.703319787979126,
+      "learning_rate": 9.077868852459017e-05,
+      "loss": 5.4567,
+      "step": 1176
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.44967794418335,
+      "eval_runtime": 19.3703,
+      "eval_samples_per_second": 1301.531,
+      "eval_steps_per_second": 5.111,
+      "step": 1176
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7449887990951538,
+      "learning_rate": 8.542349726775956e-05,
+      "loss": 5.3291,
+      "step": 1568
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.36224889755249,
+      "eval_runtime": 19.3778,
+      "eval_samples_per_second": 1301.028,
+      "eval_steps_per_second": 5.109,
+      "step": 1568
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7372640371322632,
+      "learning_rate": 8.006830601092896e-05,
+      "loss": 5.2305,
+      "step": 1960
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.299103260040283,
+      "eval_runtime": 19.3631,
+      "eval_samples_per_second": 1302.012,
+      "eval_steps_per_second": 5.113,
+      "step": 1960
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.8692474961280823,
+      "learning_rate": 7.471311475409837e-05,
+      "loss": 5.1455,
+      "step": 2352
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 5.251907825469971,
+      "eval_runtime": 19.6411,
+      "eval_samples_per_second": 1283.586,
+      "eval_steps_per_second": 5.04,
+      "step": 2352
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8557842969894409,
+      "learning_rate": 6.935792349726776e-05,
+      "loss": 5.0685,
+      "step": 2744
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 5.212622165679932,
+      "eval_runtime": 19.4624,
+      "eval_samples_per_second": 1295.37,
+      "eval_steps_per_second": 5.087,
+      "step": 2744
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.9237802624702454,
+      "learning_rate": 6.400273224043716e-05,
+      "loss": 4.9973,
+      "step": 3136
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 5.183369159698486,
+      "eval_runtime": 19.3362,
+      "eval_samples_per_second": 1303.827,
+      "eval_steps_per_second": 5.12,
+      "step": 3136
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.9417304992675781,
+      "learning_rate": 5.864754098360656e-05,
+      "loss": 4.9306,
+      "step": 3528
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 5.16442346572876,
+      "eval_runtime": 19.4148,
+      "eval_samples_per_second": 1298.546,
+      "eval_steps_per_second": 5.099,
+      "step": 3528
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.036487340927124,
+      "learning_rate": 5.329234972677596e-05,
+      "loss": 4.8677,
+      "step": 3920
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 5.1533684730529785,
+      "eval_runtime": 19.4796,
+      "eval_samples_per_second": 1294.227,
+      "eval_steps_per_second": 5.082,
+      "step": 3920
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.683262271488e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0744736c0941a6516ac30bfd0951ac43f998424fdd37d40842011ca82121f54d
+size 5905