Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e3679f93130a2d69acee23a11603616ae6cdb9967fd9e6ba71df2edc275d9c
+oid sha256:35caabf036f0fc88d5327c2435129964284a503d21f924f2a30ca4de90d532be
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65e2b234cf06ef0a7d2c5aa3144763efccc7941f32fecd3814d2d8984f0f5780
+oid sha256:6c78fd38361e00edd0e3a42df821a98cff016981283e9adf10f136e72dd70832
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e300bddb0d7e7d6e026d32cddc3203212379cd7e7d4945e7775d35a028e0ce1f
+oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007620934707641893,
+  "epoch": 0.0015241869415283786,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 6.5638,
       "step": 9
+    },
+    {
+      "epoch": 0.0009145121649170271,
+      "grad_norm": 1.8017927408218384,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 6.3315,
+      "step": 12
+    },
+    {
+      "epoch": 0.0011431402061462838,
+      "grad_norm": 1.7953505516052246,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 5.1193,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012193495532227027,
+      "eval_loss": 1.4005733728408813,
+      "eval_runtime": 570.8146,
+      "eval_samples_per_second": 9.679,
+      "eval_steps_per_second": 4.84,
+      "step": 16
+    },
+    {
+      "epoch": 0.0013717682473755406,
+      "grad_norm": 1.3931858539581299,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.2299,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1842091508367360.0,
+  "total_flos": 3684183016734720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null