Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e114e3d3892d0895423ad138937ea9512fc197ca31b28b2a10155668a5f8152
+oid sha256:d2a47ee8f8d2556347810d6a7ffd8d995d927c54beda199dd2fe7e20547c6dff
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ad0adb6af98056d3229cfa0fc6db2180f75f05035fc4d28ab3517280ffac67
+oid sha256:0621047e1b5d66fd24ee4e3f3ec49c303c0cf2ac713c59094365f0b1f955bc71
 size 45221242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e1abc6529582bc597a1cf37095dd09b36a6879413f7b6d8a94b140563ed578c
+oid sha256:97d9970a3abb203bf0ae82b39413e14be5c71c88fecae3a9686c1446eb59ade1
 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": 0.004172461752433936,
+  "epoch": 0.008344923504867872,
   "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": 30.641,
       "eval_steps_per_second": 30.641,
       "step": 3
+    },
+    {
+      "epoch": 0.005563282336578581,
+      "grad_norm": 1.0017286539077759,
+      "learning_rate": 8e-05,
+      "loss": 0.8552,
+      "step": 4
+    },
+    {
+      "epoch": 0.006954102920723227,
+      "grad_norm": 1.0567864179611206,
+      "learning_rate": 0.0001,
+      "loss": 0.9583,
+      "step": 5
+    },
+    {
+      "epoch": 0.008344923504867872,
+      "grad_norm": 0.7813672423362732,
+      "learning_rate": 0.00012,
+      "loss": 0.8737,
+      "step": 6
+    },
+    {
+      "epoch": 0.008344923504867872,
+      "eval_loss": 0.9795357584953308,
+      "eval_runtime": 5.1418,
+      "eval_samples_per_second": 29.562,
+      "eval_steps_per_second": 29.562,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 72163654631424.0,
+  "total_flos": 156354585034752.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null