Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d27f00ea039627c2ef9586342463b5e0aa9bc0e3521f0a3047adb9079ceeca0
+oid sha256:4585d74a7cea9b129114941cdbfefa26a81469178f2fc74184c57fe53ba71e10
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eaa1d3b61ca9f08c7d810cd09f9823fdd771f14f60ffb8a9a2a0665b26c5eec
+oid sha256:3e1298a2bcb6bb380f78482320d66236739c2685143ca749141b12eabaf82ed3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05531349f6e2487143a7251afc8a645033108171aa1d481234785012b46d00ef
+oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
 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": 0.0057306590257879654,
+  "epoch": 0.011461318051575931,
   "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": 17.183,
       "eval_steps_per_second": 8.63,
       "step": 3
+    },
+    {
+      "epoch": 0.007640878701050621,
+      "grad_norm": 1.1618703603744507,
+      "learning_rate": 8e-05,
+      "loss": 3.0982,
+      "step": 4
+    },
+    {
+      "epoch": 0.009551098376313277,
+      "grad_norm": 1.2491005659103394,
+      "learning_rate": 0.0001,
+      "loss": 2.8439,
+      "step": 5
+    },
+    {
+      "epoch": 0.011461318051575931,
+      "grad_norm": 1.0564581155776978,
+      "learning_rate": 0.00012,
+      "loss": 3.1059,
+      "step": 6
+    },
+    {
+      "epoch": 0.011461318051575931,
+      "eval_loss": 2.8710217475891113,
+      "eval_runtime": 12.8655,
+      "eval_samples_per_second": 17.178,
+      "eval_steps_per_second": 8.628,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 2219477097775104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null