Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07630136fc80276792361e16239cccc7e125a592c73b03dbd8a93d3ddae37459
+oid sha256:63cfacd2d61ad699f2ba5bfd93efc6cae76e074f156838a2a28013931b4d0f0b
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1869fb2a0c5abdf769e87f4ce6bab2987a0d66db6344ad9062cd456d113ac646
+oid sha256:11815f4319fe649a93bb4062e36961316515762337b10cf345507e172f6b2fb7
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d8829c82d04d9ec6bacfc38deb032d975006f94a9426c44cbbf68416e46129
+oid sha256:6fd2dcf10dab10ab8ee0931b3c2ef546aa966f1aae45a22c8b6f6a0effcde90e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0016263468184590363,
+  "epoch": 0.0032526936369180726,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 2.5338,
       "step": 9
+    },
+    {
+      "epoch": 0.0019516161821508437,
+      "grad_norm": 1.2633097171783447,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.7224,
+      "step": 12
+    },
+    {
+      "epoch": 0.002439520227688555,
+      "grad_norm": 0.614086389541626,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.7872,
+      "step": 15
+    },
+    {
+      "epoch": 0.0026021549095344584,
+      "eval_loss": 0.6183476448059082,
+      "eval_runtime": 323.9576,
+      "eval_samples_per_second": 7.992,
+      "eval_steps_per_second": 3.997,
+      "step": 16
+    },
+    {
+      "epoch": 0.0029274242732262655,
+      "grad_norm": 0.567788302898407,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.1966,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9363049194455040.0,
+  "total_flos": 1.856740263985152e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null