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:f7a5bc27d15a98a1b7f008e2ae5b1fa71f8564b2203bc5f567718fee9c9b8de9
+oid sha256:917b9908d6ddf96c924657a17ab9a77947c3dee4187dc99733d028b7da01a370
 size 17425352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dfc1b4acfe0978bca370fbc004221ea2fea4474ce49223be7246d9be15c336c
-size 10251668
+oid sha256:63574ea2b3926287ca101305d0da3612adfdea5a67b7f1e2bae3ca77824eb182
+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": 141.18,
       "eval_steps_per_second": 17.656,
       "step": 200
+    },
+    {
+      "epoch": 0.05331252844418438,
+      "grad_norm": 0.2229231297969818,
+      "learning_rate": 5e-05,
+      "loss": 2.4477,
+      "step": 205
+    },
+    {
+      "epoch": 0.05461283401599376,
+      "grad_norm": 0.22189436852931976,
+      "learning_rate": 4.798670299452926e-05,
+      "loss": 2.4228,
+      "step": 210
+    },
+    {
+      "epoch": 0.05591313958780313,
+      "grad_norm": 0.21090376377105713,
+      "learning_rate": 4.597667156416371e-05,
+      "loss": 2.3939,
+      "step": 215
+    },
+    {
+      "epoch": 0.05721344515961251,
+      "grad_norm": 0.20227909088134766,
+      "learning_rate": 4.397316598723385e-05,
+      "loss": 2.37,
+      "step": 220
+    },
+    {
+      "epoch": 0.058513750731421885,
+      "grad_norm": 0.21790654957294464,
+      "learning_rate": 4.197943595711198e-05,
+      "loss": 2.4721,
+      "step": 225
+    },
+    {
+      "epoch": 0.05981405630323126,
+      "grad_norm": 0.1942271739244461,
+      "learning_rate": 3.9998715311197785e-05,
+      "loss": 2.4373,
+      "step": 230
+    },
+    {
+      "epoch": 0.061114361875040636,
+      "grad_norm": 0.20492784678936005,
+      "learning_rate": 3.803421678562213e-05,
+      "loss": 2.4142,
+      "step": 235
+    },
+    {
+      "epoch": 0.06241466744685001,
+      "grad_norm": 0.23484589159488678,
+      "learning_rate": 3.608912680417737e-05,
+      "loss": 2.5037,
+      "step": 240
+    },
+    {
+      "epoch": 0.06371497301865939,
+      "grad_norm": 0.20387956500053406,
+      "learning_rate": 3.4166600309926387e-05,
+      "loss": 2.4313,
+      "step": 245
+    },
+    {
+      "epoch": 0.06501527859046877,
+      "grad_norm": 0.21440523862838745,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 2.3804,
+      "step": 250
+    },
+    {
+      "epoch": 0.06631558416227813,
+      "grad_norm": 0.21894583106040955,
+      "learning_rate": 3.0401669506996256e-05,
+      "loss": 2.3944,
+      "step": 255
+    },
+    {
+      "epoch": 0.06761588973408751,
+      "grad_norm": 0.23404517769813538,
+      "learning_rate": 2.8565371929847284e-05,
+      "loss": 2.4495,
+      "step": 260
+    },
+    {
+      "epoch": 0.06891619530589689,
+      "grad_norm": 0.22827592492103577,
+      "learning_rate": 2.6763841397811573e-05,
+      "loss": 2.4284,
+      "step": 265
+    },
+    {
+      "epoch": 0.07021650087770626,
+      "grad_norm": 0.2367011457681656,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.4119,
+      "step": 270
+    },
+    {
+      "epoch": 0.07151680644951564,
+      "grad_norm": 0.23400311172008514,
+      "learning_rate": 2.3276708693609943e-05,
+      "loss": 2.5657,
+      "step": 275
+    },
+    {
+      "epoch": 0.07281711202132501,
+      "grad_norm": 0.22112374007701874,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 2.5174,
+      "step": 280
+    },
+    {
+      "epoch": 0.07411741759313438,
+      "grad_norm": 0.22433413565158844,
+      "learning_rate": 1.996288678810105e-05,
+      "loss": 2.4226,
+      "step": 285
+    },
+    {
+      "epoch": 0.07541772316494376,
+      "grad_norm": 0.21052949130535126,
+      "learning_rate": 1.837773122023114e-05,
+      "loss": 2.4243,
+      "step": 290
+    },
+    {
+      "epoch": 0.07671802873675314,
+      "grad_norm": 0.21205665171146393,
+      "learning_rate": 1.684386708796025e-05,
+      "loss": 2.4338,
+      "step": 295
+    },
+    {
+      "epoch": 0.07801833430856252,
+      "grad_norm": 0.23179137706756592,
+      "learning_rate": 1.536378232452003e-05,
+      "loss": 2.3962,
+      "step": 300
+    },
+    {
+      "epoch": 0.07801833430856252,
+      "eval_loss": 2.4198389053344727,
+      "eval_runtime": 45.9519,
+      "eval_samples_per_second": 140.952,
+      "eval_steps_per_second": 17.627,
+      "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