Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60e82e353ac49e14b59f48338c588b96f630c2e1220360eb1efd43fc351742c8
+oid sha256:11457852c55de6354dba794ddab21ae2d61155de64922d9b7d00a4456c9b5453
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83432036b213f618095229b02501dcacbc7218b8eea3874836e93174fcc7196f
+oid sha256:46ec355f687465e29dd8752c6fb8d59808aa41d0fe3ac33a0bd8bd7b8be94e5b
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcf3a38473cd643bea98728742b3dba11b05cdbb4ed09b8adb4a881205bc1d44
+oid sha256:fe300d7c5ab10b566794c92461448fbc4b1030e2c8290ab8f4cd627fc33f0bc0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000507292327203551,
+  "epoch": 0.001014584654407102,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 29.189,
       "eval_steps_per_second": 14.594,
       "step": 3
+    },
+    {
+      "epoch": 0.0006763897696047348,
+      "grad_norm": 8.044904708862305,
+      "learning_rate": 8e-05,
+      "loss": 6.3287,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008454872120059184,
+      "grad_norm": 8.073067665100098,
+      "learning_rate": 0.0001,
+      "loss": 6.4404,
+      "step": 5
+    },
+    {
+      "epoch": 0.001014584654407102,
+      "grad_norm": 7.195446491241455,
+      "learning_rate": 0.00012,
+      "loss": 5.6174,
+      "step": 6
+    },
+    {
+      "epoch": 0.001014584654407102,
+      "eval_loss": 5.374767780303955,
+      "eval_runtime": 85.5385,
+      "eval_samples_per_second": 29.11,
+      "eval_steps_per_second": 14.555,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 377083649851392.0,
+  "total_flos": 719886967898112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null