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:a0922972bdac01960ba00df7884392eba7d4943bab547bfbfa075badf4630c0c
+oid sha256:0e68ed783a6ab0ad15b9d41da1259e4042acc85f8b9c587eb056553716bb0f3e
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578089bcb6e465158624daac090d3fabee24ea8fabf310f572ef984081bfa081
+oid sha256:5853ce6fec559e631fdff67287a9ce3657ed52f65eb7b7dad49a843a9f9913da
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff226c15e19b8085e09f0025aa31f4d46c591e213735b264a5e28d7f9728a70c
+oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
 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": 0.0016875856977112118,
+  "epoch": 0.0033751713954224237,
   "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": 134.349,
       "eval_steps_per_second": 67.175,
       "step": 5
+    },
+    {
+      "epoch": 0.0020251028372534545,
+      "grad_norm": 5.740655899047852,
+      "learning_rate": 6e-05,
+      "loss": 3.7718,
+      "step": 6
+    },
+    {
+      "epoch": 0.0023626199767956967,
+      "grad_norm": 5.769639015197754,
+      "learning_rate": 7e-05,
+      "loss": 3.8983,
+      "step": 7
+    },
+    {
+      "epoch": 0.002700137116337939,
+      "grad_norm": 5.479471683502197,
+      "learning_rate": 8e-05,
+      "loss": 3.2239,
+      "step": 8
+    },
+    {
+      "epoch": 0.0030376542558801815,
+      "grad_norm": 5.583406448364258,
+      "learning_rate": 9e-05,
+      "loss": 3.1888,
+      "step": 9
+    },
+    {
+      "epoch": 0.0033751713954224237,
+      "grad_norm": 5.544492721557617,
+      "learning_rate": 0.0001,
+      "loss": 3.2513,
+      "step": 10
+    },
+    {
+      "epoch": 0.0033751713954224237,
+      "eval_loss": 2.91571044921875,
+      "eval_runtime": 51.272,
+      "eval_samples_per_second": 97.324,
+      "eval_steps_per_second": 48.662,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 153447605207040.0,
+  "total_flos": 306895210414080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null