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:d574fc2eae52235df286294e225878782b5a0a57984851ebcca2183630c60677
+oid sha256:36782ed6d4c9968c620e2246c4d19cb5d4f958e78ba56904cf68ab02980c7474
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83b57584209bee0275b12c5eb1d3cd7ef5d628dd27454f7bad93d10cde13632
+oid sha256:fa3502774ac0333793c32421fcccd2cf9f9ff5f5a4fc537c4e0c17a4b140d0f2
 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": 0.014986886474334956,
+  "epoch": 0.029973772948669913,
   "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": 41.115,
       "eval_steps_per_second": 20.558,
       "step": 5
+    },
+    {
+      "epoch": 0.01798426376920195,
+      "grad_norm": 1.8076452016830444,
+      "learning_rate": 6e-05,
+      "loss": 1.1487,
+      "step": 6
+    },
+    {
+      "epoch": 0.02098164106406894,
+      "grad_norm": 2.2778992652893066,
+      "learning_rate": 7e-05,
+      "loss": 1.2715,
+      "step": 7
+    },
+    {
+      "epoch": 0.02397901835893593,
+      "grad_norm": 2.0399832725524902,
+      "learning_rate": 8e-05,
+      "loss": 0.8026,
+      "step": 8
+    },
+    {
+      "epoch": 0.026976395653802922,
+      "grad_norm": 2.653815984725952,
+      "learning_rate": 9e-05,
+      "loss": 0.7842,
+      "step": 9
+    },
+    {
+      "epoch": 0.029973772948669913,
+      "grad_norm": 2.3324148654937744,
+      "learning_rate": 0.0001,
+      "loss": 0.6289,
+      "step": 10
+    },
+    {
+      "epoch": 0.029973772948669913,
+      "eval_loss": 0.659218966960907,
+      "eval_runtime": 13.6822,
+      "eval_samples_per_second": 41.075,
+      "eval_steps_per_second": 20.538,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3745367602495488.0,
+  "total_flos": 7444496098787328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null