Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382ef070b8dc03937a601095f70f70d50dbe55eefcaca41684eff829dae86e6d
+oid sha256:ec21617278dd1d7faaa48a48d01ff72c5098fb9c0a0492af69a37ab67d6acbea
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd57bb559aeb4848e2c7dcdcd5004cf13a9843584cc6bbcf68d6766d787f3696
+oid sha256:e3cf85b625fd864d7bb72ff7e628d4b1779cb6be3374bde60f312e0ff80cc628
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac108aa9eba00358310a4439f789a188dfe5197c585ee0c9b69af254e4ad32c
+oid sha256:4a39a41f912d3765e4194e7bf2d118cba79dcbe423e3417f95fa83853160b690
 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": 0.023962857570765314,
+  "epoch": 0.03594428635614797,
   "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": 7.671,
       "eval_steps_per_second": 3.841,
       "step": 10
+    },
+    {
+      "epoch": 0.026359143327841845,
+      "grad_norm": 0.25037920475006104,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.9432,
+      "step": 11
+    },
+    {
+      "epoch": 0.028755429084918377,
+      "grad_norm": 0.2890665829181671,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.9455,
+      "step": 12
+    },
+    {
+      "epoch": 0.03115171484199491,
+      "grad_norm": 0.25389617681503296,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.8939,
+      "step": 13
+    },
+    {
+      "epoch": 0.03354800059907144,
+      "grad_norm": 0.2094624787569046,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.8387,
+      "step": 14
+    },
+    {
+      "epoch": 0.03594428635614797,
+      "grad_norm": 0.21110887825489044,
+      "learning_rate": 5e-05,
+      "loss": 0.8639,
+      "step": 15
+    },
+    {
+      "epoch": 0.03594428635614797,
+      "eval_loss": 0.8595573306083679,
+      "eval_runtime": 91.6996,
+      "eval_samples_per_second": 7.666,
+      "eval_steps_per_second": 3.839,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.310019224076288e+16,
+  "total_flos": 1.969148393422848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null