Add checkpoint checkpoint-132

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1162765a6319f7f68282e5300e0930620e1971cf6266d446ae62abe9020ea18
+size 667923768

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fee78cfa77a28b5834bdaac92cbbfd454d9a9f5ab9032d8fbb47be7de66bf2d1
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f65351b47020b44f4c5d61cd4199048f24e9495db862cf9334ffc6d5ec5a6fc
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f0ee748aacc2da7f390e632f44bb55a0b56a07162587ea7280962f448f9dda
+size 1064

trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 132,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 173.64956665039062,
+      "learning_rate": 2e-05,
+      "loss": 7.0527,
+      "step": 10
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 121.92434692382812,
+      "learning_rate": 1.9700312531945444e-05,
+      "loss": 4.131,
+      "step": 20
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 18.577713012695312,
+      "learning_rate": 1.881921264348355e-05,
+      "loss": 1.0488,
+      "step": 30
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 1.1142139434814453,
+      "learning_rate": 1.7409511253549592e-05,
+      "loss": 0.2425,
+      "step": 40
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.9895141124725342,
+      "learning_rate": 1.5555702330196024e-05,
+      "loss": 0.1722,
+      "step": 50
+    },
+    {
+      "epoch": 1.367816091954023,
+      "grad_norm": 0.4484473466873169,
+      "learning_rate": 1.3368898533922202e-05,
+      "loss": 0.1419,
+      "step": 60
+    },
+    {
+      "epoch": 1.5977011494252875,
+      "grad_norm": 0.369838684797287,
+      "learning_rate": 1.098017140329561e-05,
+      "loss": 0.1217,
+      "step": 70
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.39219459891319275,
+      "learning_rate": 8.532695255446384e-06,
+      "loss": 0.1209,
+      "step": 80
+    },
+    {
+      "epoch": 2.045977011494253,
+      "grad_norm": 0.3567904233932495,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.1151,
+      "step": 90
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.4065280556678772,
+      "learning_rate": 4.043006955075667e-06,
+      "loss": 0.1072,
+      "step": 100
+    },
+    {
+      "epoch": 2.5057471264367814,
+      "grad_norm": 0.44446897506713867,
+      "learning_rate": 2.26989546637263e-06,
+      "loss": 0.0978,
+      "step": 110
+    },
+    {
+      "epoch": 2.735632183908046,
+      "grad_norm": 0.3840075433254242,
+      "learning_rate": 9.601070687655667e-07,
+      "loss": 0.1075,
+      "step": 120
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 0.3778819441795349,
+      "learning_rate": 1.921471959676957e-07,
+      "loss": 0.1001,
+      "step": 130
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 132,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1148164409065472e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}