Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c70eecbb605830eed8afa6c291753906e4924192662b52c282aa211f38258c
+oid sha256:5b17243c32965b355fc9765d5b59ada896b5f0165f17d38de8d655cb6481ad6a
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609cbf6a4993f8285635eeb10c841bd596cbd605eada2cff60dd42e16c85e204
+oid sha256:789fbaec49b413c9a763b4acf09bcfe86097890aba65f2d89aea0e3452c0430f
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d761a865805231e466975dc557ac832a6f542610cb998ae0219bb55a7ba68b7d
+oid sha256:f7a18528153d6dd23c43c37e41b2823805f3d704c19995abc83179571246a672
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87d4e73dab5b4a75d4f3cf3fb27527e28899c234f2c83e5118101993055d7a25
+oid sha256:222a395289655e6330fa151479fc92b6da721e27fbeeddf74525fa4489d12a3a
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a382728146b27225e38b8e01d45648e3fa48bcb35e4b2715ad4ce673fcd096c
+oid sha256:92dfec00580cc49b39040eaf5b9c2db7f74dcfff57c6e3f25fc641f1656401d3
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c39412d919b7b82dcf9c9c10833616604451f675b8dda18c6254956563df2fe2
+oid sha256:ae40dca5e32a36e2a2c5a65c1db1aa929fb2ddcdc46c8721fde7e5f9e80b94bb
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
+oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1152,
+  "epoch": 0.1728,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 228.939,
       "eval_steps_per_second": 7.182,
       "step": 18
+    },
+    {
+      "epoch": 0.1344,
+      "grad_norm": 1.0180203914642334,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 2.1507,
+      "step": 21
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 0.8608107566833496,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 2.0623,
+      "step": 24
+    },
+    {
+      "epoch": 0.1728,
+      "grad_norm": 0.8825973272323608,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.1129,
+      "step": 27
+    },
+    {
+      "epoch": 0.1728,
+      "eval_loss": 2.0721230506896973,
+      "eval_runtime": 4.6294,
+      "eval_samples_per_second": 227.245,
+      "eval_steps_per_second": 7.128,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9053119979585536e+16,
+  "total_flos": 4.362994477694976e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null