Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef879876d21dbdadbfd558cf0e0ddbce9209d17170e87020a3fabae9bbc33ec3
+oid sha256:871feece1869ec94f4898ad14e5ff0c917acf15e1816eef7828c3465fd89210d
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d7bb5b6e5c91005be9ca90b56732b6cdd43aa7495e5bf78fe7894e95fa7e9da
+oid sha256:b9bd5dba385cef38cf4aaa4d08bfe388ca3157778768fb10f7fcc8f1530b1dee
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c8ae2cb1e582e9310963ad3ed8b41f0acd771a18e5c2e6e9ee8cbbe52fdc3cd
+oid sha256:359d0ddb346e1a051d153b9361e52227f5a93bfd11d7d59f8d34fe81bcaff9e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028303555634176542,
+  "epoch": 0.056607111268353084,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 75.591,
       "eval_steps_per_second": 37.859,
       "step": 5
+    },
+    {
+      "epoch": 0.03396426676101185,
+      "grad_norm": 0.23880141973495483,
+      "learning_rate": 6e-05,
+      "loss": 10.4333,
+      "step": 6
+    },
+    {
+      "epoch": 0.03962497788784716,
+      "grad_norm": 0.2584647536277771,
+      "learning_rate": 7e-05,
+      "loss": 10.4085,
+      "step": 7
+    },
+    {
+      "epoch": 0.04528568901468247,
+      "grad_norm": 0.22347287833690643,
+      "learning_rate": 8e-05,
+      "loss": 10.4365,
+      "step": 8
+    },
+    {
+      "epoch": 0.05094640014151778,
+      "grad_norm": 0.25124576687812805,
+      "learning_rate": 9e-05,
+      "loss": 10.4249,
+      "step": 9
+    },
+    {
+      "epoch": 0.056607111268353084,
+      "grad_norm": 0.25805941224098206,
+      "learning_rate": 0.0001,
+      "loss": 10.4151,
+      "step": 10
+    },
+    {
+      "epoch": 0.056607111268353084,
+      "eval_loss": 10.431522369384766,
+      "eval_runtime": 7.8709,
+      "eval_samples_per_second": 75.595,
+      "eval_steps_per_second": 37.861,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4184195727360.0,
+  "total_flos": 8368391454720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null