Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcce981e1fc90247a2a19fd214052163c440c6ebc7ee92517236d831d2b5ac53
+size 2708729576

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac772a5d04330763a04918482c2b2ed91de57cfc8571b776ae577c7ae6d0893
+size 52499200

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35b4cd4104958a3e34a87e84eee852763c80157fefbeae8abd4d6ed6ea94168
+size 15006

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca4dbe650e04bc8012dd3f1938dfb2a637329721abd75c3bd59d28a64007b54
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 129,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3904343582235237,
+      "grad_norm": 1104.4410400390625,
+      "learning_rate": 9.609375e-05,
+      "loss": 24.0156,
+      "step": 50
+    },
+    {
+      "epoch": 0.3904343582235237,
+      "eval_runtime": 19.6625,
+      "eval_samples_per_second": 21.971,
+      "eval_steps_per_second": 5.493,
+      "step": 50
+    },
+    {
+      "epoch": 0.7808687164470474,
+      "grad_norm": 808.6486206054688,
+      "learning_rate": 9.21875e-05,
+      "loss": 8.6753,
+      "step": 100
+    },
+    {
+      "epoch": 0.7808687164470474,
+      "eval_runtime": 19.6174,
+      "eval_samples_per_second": 22.021,
+      "eval_steps_per_second": 5.505,
+      "step": 100
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 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:f660b4b1a4e6875e18f0159f38be0abdeee84d927a7ae5ea529258f8868649bb
+size 5368