Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caec0d86ab99eee6cff14ca87c82a867148f70a209126f9aa6e011e3684228dc
+oid sha256:b0e6f53d6607615df544562b53c177c597c7c7764cc3cb9a82154924eabc9d19
 size 17425352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:688e7e0105fdeecfbd76140dca9c778ab27df9f4d6f0e48b9217d7a131ba0908
-size 10251668
+oid sha256:aff84825d6486fa6b4465aee818af4c7da4806e1a370db24ba58ba40c23073ff
+size 10252116

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd619ac5fe1b5a9993caa1b33027cbaba2affae2b385b5b8e1edc744130828b6
+oid sha256:49c3113ab5e74cf2cf75b8272697182349b986f05fea887c23c6b1cf30a10723
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ce9f7304e0a4744e6ea3362c37f41fa81110af8aa0741e1543ca9d0f005e0bc
+oid sha256:948034a5628471bb3c37b4e388f6a1656b75ee096cbb96c84fa1a5c61b6c63e2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2663b0191a48b0d84f57520e6d7470d2ed946f6d4e667618a3101ba08ea341a
+oid sha256:e03f9a24a7a90769559ab2186e52e4bea52a0ca73705b5babf1706779cbc29f3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d803133439c81a4ccfa134ee0737fabb2479f40d1f31268b7cfb1fa6f46236
+oid sha256:36ecb369e890de96dc252a97d723cd39a5de3933ea7d729b6a84c9264b7d8b05
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac116b8169c53ab649a7f15f2f32735f2c71ec2f803f70de8c655a513ee9cfc
+oid sha256:43da0688aca60835f4e18fa7e0f3cc099504828f82fd5dd994118be26b760a0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05201222287237501,
+  "epoch": 0.07801833430856252,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -311,6 +311,154 @@
       "eval_samples_per_second": 132.872,
       "eval_steps_per_second": 16.617,
       "step": 200
+    },
+    {
+      "epoch": 0.05331252844418438,
+      "grad_norm": 0.22658920288085938,
+      "learning_rate": 5e-05,
+      "loss": 2.4468,
+      "step": 205
+    },
+    {
+      "epoch": 0.05461283401599376,
+      "grad_norm": 0.22382205724716187,
+      "learning_rate": 4.798670299452926e-05,
+      "loss": 2.4227,
+      "step": 210
+    },
+    {
+      "epoch": 0.05591313958780313,
+      "grad_norm": 0.2128317654132843,
+      "learning_rate": 4.597667156416371e-05,
+      "loss": 2.394,
+      "step": 215
+    },
+    {
+      "epoch": 0.05721344515961251,
+      "grad_norm": 0.20399969816207886,
+      "learning_rate": 4.397316598723385e-05,
+      "loss": 2.3722,
+      "step": 220
+    },
+    {
+      "epoch": 0.058513750731421885,
+      "grad_norm": 0.22103694081306458,
+      "learning_rate": 4.197943595711198e-05,
+      "loss": 2.4722,
+      "step": 225
+    },
+    {
+      "epoch": 0.05981405630323126,
+      "grad_norm": 0.19609223306179047,
+      "learning_rate": 3.9998715311197785e-05,
+      "loss": 2.4358,
+      "step": 230
+    },
+    {
+      "epoch": 0.061114361875040636,
+      "grad_norm": 0.20797300338745117,
+      "learning_rate": 3.803421678562213e-05,
+      "loss": 2.4147,
+      "step": 235
+    },
+    {
+      "epoch": 0.06241466744685001,
+      "grad_norm": 0.23733116686344147,
+      "learning_rate": 3.608912680417737e-05,
+      "loss": 2.5038,
+      "step": 240
+    },
+    {
+      "epoch": 0.06371497301865939,
+      "grad_norm": 0.20630250871181488,
+      "learning_rate": 3.4166600309926387e-05,
+      "loss": 2.43,
+      "step": 245
+    },
+    {
+      "epoch": 0.06501527859046877,
+      "grad_norm": 0.21626047790050507,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 2.3791,
+      "step": 250
+    },
+    {
+      "epoch": 0.06631558416227813,
+      "grad_norm": 0.22082562744617462,
+      "learning_rate": 3.0401669506996256e-05,
+      "loss": 2.3927,
+      "step": 255
+    },
+    {
+      "epoch": 0.06761588973408751,
+      "grad_norm": 0.2386007159948349,
+      "learning_rate": 2.8565371929847284e-05,
+      "loss": 2.4492,
+      "step": 260
+    },
+    {
+      "epoch": 0.06891619530589689,
+      "grad_norm": 0.23111873865127563,
+      "learning_rate": 2.6763841397811573e-05,
+      "loss": 2.4282,
+      "step": 265
+    },
+    {
+      "epoch": 0.07021650087770626,
+      "grad_norm": 0.23999303579330444,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.4116,
+      "step": 270
+    },
+    {
+      "epoch": 0.07151680644951564,
+      "grad_norm": 0.23608632385730743,
+      "learning_rate": 2.3276708693609943e-05,
+      "loss": 2.5647,
+      "step": 275
+    },
+    {
+      "epoch": 0.07281711202132501,
+      "grad_norm": 0.22393612563610077,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 2.516,
+      "step": 280
+    },
+    {
+      "epoch": 0.07411741759313438,
+      "grad_norm": 0.2267947643995285,
+      "learning_rate": 1.996288678810105e-05,
+      "loss": 2.4214,
+      "step": 285
+    },
+    {
+      "epoch": 0.07541772316494376,
+      "grad_norm": 0.21349841356277466,
+      "learning_rate": 1.837773122023114e-05,
+      "loss": 2.4265,
+      "step": 290
+    },
+    {
+      "epoch": 0.07671802873675314,
+      "grad_norm": 0.21270251274108887,
+      "learning_rate": 1.684386708796025e-05,
+      "loss": 2.4332,
+      "step": 295
+    },
+    {
+      "epoch": 0.07801833430856252,
+      "grad_norm": 0.23567631840705872,
+      "learning_rate": 1.536378232452003e-05,
+      "loss": 2.396,
+      "step": 300
+    },
+    {
+      "epoch": 0.07801833430856252,
+      "eval_loss": 2.4196038246154785,
+      "eval_runtime": 47.2697,
+      "eval_samples_per_second": 137.022,
+      "eval_steps_per_second": 17.136,
+      "step": 300
     }
   ],
   "logging_steps": 5,
@@ -330,7 +478,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.271906598649856e+16,
+  "total_flos": 1.905704121348915e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null