Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e3cc8e04cedc525347989eedeef5e6871430b0c568bcc4f0f19c6a604d9ef0
+oid sha256:eb0ebb3e2ac05525b1b13844e3b5194663545674f759fd46377f6b265d732e23
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae5707fd45824773fec83395c846325bf944da931b472aac5c9d9e2af32528f1
+oid sha256:3a5606e4f7e3aa00a34b24dc60eceb28f1981f7886586b29e4084e5e104fa1fd
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
+oid sha256:376a84af6354b555ba2fbd8c3fc92d9086d0a9dcf2c9793e8d456dbd561d4eb5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002198266751215388,
+  "epoch": 0.004396533502430776,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 17.184,
       "eval_steps_per_second": 8.592,
       "step": 10
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "grad_norm": 2.685682535171509,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.4402,
+      "step": 15
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "grad_norm": 2.484118938446045,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.1726,
+      "step": 20
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "eval_loss": 0.13887104392051697,
+      "eval_runtime": 145.2477,
+      "eval_samples_per_second": 17.143,
+      "eval_steps_per_second": 8.572,
+      "step": 20
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "grad_norm": 1.2602101564407349,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1889,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2117353076686848.0,
+  "total_flos": 4234706153373696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null