Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472fc5f2fd1b5ce8fb5089998dee36e589584597f037e48d76797bc69ad65ce6
+oid sha256:d018ef538c0304abf2cbc034e4a27d33f0ace4dbb0a7ed3d6bf1ba98d7e8c26d
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6bfe686102f78ae68b2d67bc9e4bc2d36bc8a6d0063caf9fc994422e5cbe9c
+oid sha256:708aacd2eab3f30c4ce73e46665401a347007898f0f52f8e3e3bd93d8a62deb8
 size 6614970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008918120506103338,
+  "epoch": 0.013377180759155009,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 81.308,
       "eval_steps_per_second": 40.675,
       "step": 10
+    },
+    {
+      "epoch": 0.009809932556713672,
+      "grad_norm": 4.094559669494629,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 11.7451,
+      "step": 11
+    },
+    {
+      "epoch": 0.010701744607324006,
+      "grad_norm": 3.5948903560638428,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 6.9043,
+      "step": 12
+    },
+    {
+      "epoch": 0.01159355665793434,
+      "grad_norm": 3.7772586345672607,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 8.2246,
+      "step": 13
+    },
+    {
+      "epoch": 0.012485368708544674,
+      "grad_norm": 3.5396769046783447,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 12.3979,
+      "step": 14
+    },
+    {
+      "epoch": 0.013377180759155009,
+      "grad_norm": 5.234291076660156,
+      "learning_rate": 5e-05,
+      "loss": 4.1699,
+      "step": 15
+    },
+    {
+      "epoch": 0.013377180759155009,
+      "eval_loss": 0.41440320014953613,
+      "eval_runtime": 23.136,
+      "eval_samples_per_second": 81.648,
+      "eval_steps_per_second": 40.845,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 593050258636800.0,
+  "total_flos": 893328870604800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null