Training in progress, step 9600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39e431d6db14e51f3bfd3017080e7c94298c420741f672d6f3148988bcf43745
+oid sha256:757dda966b2f4d181a128ff59f9b919daff4e506360c00213ab3ec0c0ff2691e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47316673d6aef1c18ee7837cde7ac0a757dd5c2cc276a7a155156bdf8656a755
+oid sha256:07c1cbeda60e9c2a4013fcd83f0f4b91298e0a0b17ca0cb5693b8fb2316ae9ce
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0a546ed2b8311cd8322b8ea0cc1f69ea556efe2ecf55c1d3cb250225b29c7f7
+oid sha256:83bf192647771b3f8523529c1a3c6ebe56340eb008266267aa5af12c0294e34e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7b4d6e372191605987a3472222b6d31492e591157775ac3ab363680ff12d47e
+oid sha256:ce7729d52ceb1dabda5590c3c4f3afbbf1ca186490116815086c48ad76afb3f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0069904327747184304,
+  "epoch": 0.007139165386946482,
   "eval_steps": 2000,
-  "global_step": 9400,
+  "global_step": 9600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -336,6 +336,13 @@
       "learning_rate": 1.9999903767717127e-05,
       "loss": 1.5388,
       "step": 9400
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.206201076507568,
+      "learning_rate": 1.9999899624269806e-05,
+      "loss": 1.5278,
+      "step": 9600
     }
   ],
   "logging_steps": 200,
@@ -343,7 +350,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.2315378716430336e+17,
+  "total_flos": 1.2573875538675302e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null