Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175055a93714fb852fe6504cb5eacddf091fc3c8d6216835ffa0bcfc0b93e929
+oid sha256:edd75f850f6a9712b874fa815b34d1415b0c1c6a668dd4f8cc0cd6952f1098a0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:437bdbd5e649dbec8288fce41e17a39aca6b4708c8bdce68986ded5cefeac03d
+oid sha256:5a9586f5099843f7559f4e96031b0d93f3b31308c2295efdba7673c034c2a2fe
 size 43122580

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": 0.008506113769271665,
+  "epoch": 0.01701222753854333,
   "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": 8.546,
       "eval_steps_per_second": 4.273,
       "step": 5
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 0.26034078001976013,
+      "learning_rate": 6e-05,
+      "loss": 0.6896,
+      "step": 6
+    },
+    {
+      "epoch": 0.01190855927698033,
+      "grad_norm": 0.24086257815361023,
+      "learning_rate": 7e-05,
+      "loss": 0.6932,
+      "step": 7
+    },
+    {
+      "epoch": 0.013609782030834662,
+      "grad_norm": 0.26397573947906494,
+      "learning_rate": 8e-05,
+      "loss": 0.6424,
+      "step": 8
+    },
+    {
+      "epoch": 0.015311004784688996,
+      "grad_norm": 0.2352258712053299,
+      "learning_rate": 9e-05,
+      "loss": 0.6817,
+      "step": 9
+    },
+    {
+      "epoch": 0.01701222753854333,
+      "grad_norm": 0.23862141370773315,
+      "learning_rate": 0.0001,
+      "loss": 0.6594,
+      "step": 10
+    },
+    {
+      "epoch": 0.01701222753854333,
+      "eval_loss": 0.6520625948905945,
+      "eval_runtime": 118.9382,
+      "eval_samples_per_second": 8.324,
+      "eval_steps_per_second": 4.162,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6011083806474240.0,
+  "total_flos": 1.2068406719152128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null