Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7ee2006dfa912544e532a7ddbb48864d6e1af3cb27c9c3a32b96dbe4ea864c
+oid sha256:5af105525370eec15b17484216a97d4d9480e8f0820c925aeef92384a70380da
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3693b4ef87053532077ec4b2b92e2519725478540da40e7b6b4541d90ea147
+oid sha256:d6bb36cb9ad15841030dda728d353affdde511cff8583c118ebf2d3000f7f488
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb545f8e58697058fbefb3de9020d83f15fa2aa26ad3230bc2a6d11766abf95
+oid sha256:4a040b3377ea29e2e573174f608927490657c8c978fdb95169126a63ddf2673b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0506649778340722,
+  "epoch": 0.0759974667511083,
   "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": 0.0002,
       "loss": 1.0191,
       "step": 10
+    },
+    {
+      "epoch": 0.05573147561747942,
+      "grad_norm": 3.5135035514831543,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.4289,
+      "step": 11
+    },
+    {
+      "epoch": 0.060797973400886635,
+      "grad_norm": 3.6494600772857666,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.3012,
+      "step": 12
+    },
+    {
+      "epoch": 0.060797973400886635,
+      "eval_loss": 0.1743772327899933,
+      "eval_runtime": 17.1197,
+      "eval_samples_per_second": 9.755,
+      "eval_steps_per_second": 4.907,
+      "step": 12
+    },
+    {
+      "epoch": 0.06586447118429385,
+      "grad_norm": 1.6839953660964966,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.1816,
+      "step": 13
+    },
+    {
+      "epoch": 0.07093096896770108,
+      "grad_norm": 1.779843807220459,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.1379,
+      "step": 14
+    },
+    {
+      "epoch": 0.0759974667511083,
+      "grad_norm": 3.1982781887054443,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.2963,
+      "step": 15
+    },
+    {
+      "epoch": 0.0759974667511083,
+      "eval_loss": 0.11545062810182571,
+      "eval_runtime": 17.145,
+      "eval_samples_per_second": 9.74,
+      "eval_steps_per_second": 4.899,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -128,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.32218823376896e+16,
+  "total_flos": 1.98328235065344e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null