Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ed0ecede62499dc21f786d6b10dd50f0d27f71680a0a9cde907005d7ad4e9d
+oid sha256:c0dce05b630e9c2e86edbbff79488f358c363bb63689e7c14a6e58d4272ca6db
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a352ceb7f1173b6aab3bd37ced2509dabf60d77cc73088ed73d3ac026ac9b572
+oid sha256:dde531e2820073335839e972585c173b4638836d666b4f9292a8913c054a81df
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d30f820313f0ba805176b630741ffa411d41af19c4b0f5c700b700eaa0757a1
+oid sha256:aab3a91804771975540e4b79c14167f2b311d9eae66c6ec29d3118b42dc107f6
 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": 0.010978956999085087,
+  "epoch": 0.021957913998170174,
   "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": 14.775,
       "eval_steps_per_second": 7.452,
       "step": 3
+    },
+    {
+      "epoch": 0.01463860933211345,
+      "grad_norm": 0.4520469307899475,
+      "learning_rate": 8e-05,
+      "loss": 2.1588,
+      "step": 4
+    },
+    {
+      "epoch": 0.018298261665141813,
+      "grad_norm": 0.4833182692527771,
+      "learning_rate": 0.0001,
+      "loss": 2.01,
+      "step": 5
+    },
+    {
+      "epoch": 0.021957913998170174,
+      "grad_norm": 0.5507794618606567,
+      "learning_rate": 0.00012,
+      "loss": 2.1838,
+      "step": 6
+    },
+    {
+      "epoch": 0.021957913998170174,
+      "eval_loss": 2.1994447708129883,
+      "eval_runtime": 7.8005,
+      "eval_samples_per_second": 14.743,
+      "eval_steps_per_second": 7.435,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1266482172395520.0,
+  "total_flos": 2295498937466880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null