Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481549fd92bfa33b3ca3ee59d5bc352b3a2c5f4809eb649581a381291df624cc
+size 847599616

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a7cf0ed2c81fc32c151e4b208e492f66b21183d21c3703bc7d39409f809f7a
+size 1386414411

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:724cfa7d773d6c7dfa5cd8b75f76acf2e343c944007bc5ae101c6454adf55a74
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0008eaf86467511a3b74b3792388bc89587db0af5fba1e98578d98def9815f59
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 1000000000,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<|endoftext|>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,228 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.01,
+  "eval_steps": 300,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005,
+      "grad_norm": 6.011565208435059,
+      "learning_rate": 3.96e-06,
+      "loss": 20.981669921875,
+      "step": 100
+    },
+    {
+      "epoch": 0.001,
+      "grad_norm": 4.79960823059082,
+      "learning_rate": 7.96e-06,
+      "loss": 18.630086669921877,
+      "step": 200
+    },
+    {
+      "epoch": 0.0015,
+      "grad_norm": 4.753690242767334,
+      "learning_rate": 1.196e-05,
+      "loss": 17.497738037109375,
+      "step": 300
+    },
+    {
+      "epoch": 0.0015,
+      "eval_accuracy": 0.08108023483365949,
+      "eval_loss": 16.94498062133789,
+      "eval_runtime": 72.1019,
+      "eval_samples_per_second": 13.869,
+      "eval_steps_per_second": 3.467,
+      "step": 300
+    },
+    {
+      "epoch": 0.002,
+      "grad_norm": 3.2824501991271973,
+      "learning_rate": 1.596e-05,
+      "loss": 16.3246142578125,
+      "step": 400
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 4.837945461273193,
+      "learning_rate": 1.9960000000000002e-05,
+      "loss": 15.711016845703124,
+      "step": 500
+    },
+    {
+      "epoch": 0.003,
+      "grad_norm": 4.028888702392578,
+      "learning_rate": 2.396e-05,
+      "loss": 14.91444580078125,
+      "step": 600
+    },
+    {
+      "epoch": 0.003,
+      "eval_accuracy": 0.10803913894324853,
+      "eval_loss": 14.84846305847168,
+      "eval_runtime": 71.0639,
+      "eval_samples_per_second": 14.072,
+      "eval_steps_per_second": 3.518,
+      "step": 600
+    },
+    {
+      "epoch": 0.0035,
+      "grad_norm": 2.6233296394348145,
+      "learning_rate": 2.7960000000000003e-05,
+      "loss": 14.73691650390625,
+      "step": 700
+    },
+    {
+      "epoch": 0.004,
+      "grad_norm": 3.3784563541412354,
+      "learning_rate": 3.196e-05,
+      "loss": 14.402127685546875,
+      "step": 800
+    },
+    {
+      "epoch": 0.0045,
+      "grad_norm": 4.078140735626221,
+      "learning_rate": 3.596e-05,
+      "loss": 14.276339111328125,
+      "step": 900
+    },
+    {
+      "epoch": 0.0045,
+      "eval_accuracy": 0.12540117416829746,
+      "eval_loss": 14.246834754943848,
+      "eval_runtime": 70.5499,
+      "eval_samples_per_second": 14.174,
+      "eval_steps_per_second": 3.544,
+      "step": 900
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 2.698321580886841,
+      "learning_rate": 3.9960000000000004e-05,
+      "loss": 14.103670654296875,
+      "step": 1000
+    },
+    {
+      "epoch": 0.0055,
+      "grad_norm": 2.6977009773254395,
+      "learning_rate": 4.396e-05,
+      "loss": 13.91288330078125,
+      "step": 1100
+    },
+    {
+      "epoch": 0.006,
+      "grad_norm": 2.813852071762085,
+      "learning_rate": 4.796e-05,
+      "loss": 13.750213623046875,
+      "step": 1200
+    },
+    {
+      "epoch": 0.006,
+      "eval_accuracy": 0.13354794520547944,
+      "eval_loss": 13.796219825744629,
+      "eval_runtime": 70.4436,
+      "eval_samples_per_second": 14.196,
+      "eval_steps_per_second": 3.549,
+      "step": 1200
+    },
+    {
+      "epoch": 0.0065,
+      "grad_norm": 2.7015318870544434,
+      "learning_rate": 5.196e-05,
+      "loss": 13.593814697265625,
+      "step": 1300
+    },
+    {
+      "epoch": 0.007,
+      "grad_norm": 2.6103267669677734,
+      "learning_rate": 5.596e-05,
+      "loss": 13.418026123046875,
+      "step": 1400
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 2.5891685485839844,
+      "learning_rate": 5.996e-05,
+      "loss": 13.413653564453124,
+      "step": 1500
+    },
+    {
+      "epoch": 0.0075,
+      "eval_accuracy": 0.14203326810176126,
+      "eval_loss": 13.424027442932129,
+      "eval_runtime": 70.7197,
+      "eval_samples_per_second": 14.14,
+      "eval_steps_per_second": 3.535,
+      "step": 1500
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 2.7721621990203857,
+      "learning_rate": 6.396e-05,
+      "loss": 13.18080810546875,
+      "step": 1600
+    },
+    {
+      "epoch": 0.0085,
+      "grad_norm": 4.532048225402832,
+      "learning_rate": 6.796e-05,
+      "loss": 13.176103515625,
+      "step": 1700
+    },
+    {
+      "epoch": 0.009,
+      "grad_norm": 2.760545015335083,
+      "learning_rate": 7.196000000000001e-05,
+      "loss": 13.289417724609375,
+      "step": 1800
+    },
+    {
+      "epoch": 0.009,
+      "eval_accuracy": 0.1470078277886497,
+      "eval_loss": 13.157907485961914,
+      "eval_runtime": 70.4071,
+      "eval_samples_per_second": 14.203,
+      "eval_steps_per_second": 3.551,
+      "step": 1800
+    },
+    {
+      "epoch": 0.0095,
+      "grad_norm": 2.832441806793213,
+      "learning_rate": 7.596000000000001e-05,
+      "loss": 12.94510009765625,
+      "step": 1900
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.487884759902954,
+      "learning_rate": 7.996e-05,
+      "loss": 12.798345947265625,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 200000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28e2b5843184725d1b8a4fbebe4630c5d5705edaadbc1cb4642d87884e1e3e9
+size 5265