Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:151c2ac857905e8c798803a46850d1cd6811df2e0c7961fa2ef51b2d2f93546a
+oid sha256:73b972f9bc64d410480b7739f47766d1d722fa0fc4e4ccc9fa6a3929f186e043
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8cedc9c78e1423f753cf4f9ebb8215929c7db45cfc0887d45d9818e81fc0e58
+oid sha256:cb8e2ae8bef2a763205ede29820fcfd849d175722e242b18c3c051600794f73f
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77820273899338f3cb44d8b61f14d2376760c84be6dcbd25e712a3423d224d4a
+oid sha256:e0c99adfd3842a16f78adc954f43d1319a31e4bf74797a8fd450f6ab3f8c288b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abdd3b29509160214335978cbd2a63c87f2b7769a5608c5e772a6c51d699b65
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020931449502878074,
+  "epoch": 0.03139717425431711,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -109,6 +109,57 @@
       "learning_rate": 8.535533905932738e-05,
       "loss": 3.6575,
       "step": 10
+    },
+    {
+      "epoch": 0.023024594453165882,
+      "grad_norm": 5.032680988311768,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 4.096,
+      "step": 11
+    },
+    {
+      "epoch": 0.02511773940345369,
+      "grad_norm": 3.810659646987915,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 2.9131,
+      "step": 12
+    },
+    {
+      "epoch": 0.02511773940345369,
+      "eval_loss": 0.7286272644996643,
+      "eval_runtime": 28.6298,
+      "eval_samples_per_second": 7.056,
+      "eval_steps_per_second": 3.528,
+      "step": 12
+    },
+    {
+      "epoch": 0.027210884353741496,
+      "grad_norm": 2.648770570755005,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.9433,
+      "step": 13
+    },
+    {
+      "epoch": 0.029304029304029304,
+      "grad_norm": 2.9842631816864014,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 2.2262,
+      "step": 14
+    },
+    {
+      "epoch": 0.03139717425431711,
+      "grad_norm": 3.5351529121398926,
+      "learning_rate": 5e-05,
+      "loss": 2.8287,
+      "step": 15
+    },
+    {
+      "epoch": 0.03139717425431711,
+      "eval_loss": 0.5874171257019043,
+      "eval_runtime": 28.604,
+      "eval_samples_per_second": 7.062,
+      "eval_steps_per_second": 3.531,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -128,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3257498484080640.0,
+  "total_flos": 4886247726120960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null