Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b06ac304778a47745fb8abd167b7219c3320be98539733ddcd5e671da351c7
+oid sha256:f633a2899b9a0b0a35dd23cb2918b464ed0dfff73a3b36411fe0ea72204e09f7
 size 50503544

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d67d25b87527b61c91c8e7d18e57bd73f35d30287aa5b68f7112222e921af54
+oid sha256:ecb1d77f4127098da753eb5f56918d6fcfd1dd693db94a0a8d57c4221c27d8d8
 size 101199994

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5172a22bb08f1b68d12690f75b8cd3ef5e82debe9c0c3b0b77f52526c3a82a85
+oid sha256:26cfa1fb691e9923a54eb787f2d327d9f24114450d188bd6bf519aa393c61fc3
 size 50577394

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6574920222cc0afd983863e85657be4cd8aa2b22c6988e3866fcb5e10a1e03e0
+oid sha256:0f7c76b5dd7d58f0f67893500f944ce1242b822c11e35f9009bf9f8171d2317a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd353c747ce4944019f5cbb9589140851903a138c47658710efce18a66b3c49c
+oid sha256:1990fcc5f8c49c183ee5661ea2361874845f363d193c2fc8247dfee40b92fb7a
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00233836080907284,
+  "epoch": 0.00350754121360926,
   "eval_steps": 10,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 14.009,
       "eval_steps_per_second": 3.503,
       "step": 20
+    },
+    {
+      "epoch": 0.00292295101134105,
+      "grad_norm": 1.8934458494186401,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.4946,
+      "step": 25
+    },
+    {
+      "epoch": 0.00350754121360926,
+      "grad_norm": 0.7404616475105286,
+      "learning_rate": 0.0,
+      "loss": 3.4585,
+      "step": 30
+    },
+    {
+      "epoch": 0.00350754121360926,
+      "eval_loss": 3.4866576194763184,
+      "eval_runtime": 514.2075,
+      "eval_samples_per_second": 14.008,
+      "eval_steps_per_second": 3.502,
+      "step": 30
     }
   ],
   "logging_steps": 5,
@@ -73,12 +95,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4311014367559680.0,
+  "total_flos": 6466521551339520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null