Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24951095bad417fe4d5f10cb313dac59dfcfbd07da754ff9cd607089f1464f20
+oid sha256:8e3262f321176d26c6fa474fc73619945ffe32c1298cb3cb4c93f063b4f7e1cf
 size 98088784

last-checkpoint/global_step200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ec8e59fbf3708d2906da33455599161e0778f4619d48bb6157cedda10deab60
+size 73939813

last-checkpoint/global_step200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ab01ffc6b882076e872ab72450ac68242a1066b012c62a53f3ed6b1ee60adc
+size 73939813

last-checkpoint/global_step200/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54276ca1dff9468478cfda5eb668a4aef50344168b9dc23d6fb0362f4e7d8ee6
+size 73939877

last-checkpoint/global_step200/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05419254fc2f3c82d8daf23ce7e4fe0bd7fee03230281b099cb94b368801a0c
+size 73939877

last-checkpoint/global_step200/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7047707b41a4769d6c0db180802b6e4117b608ca31cdf43846bd53d4cf1fc7d8
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step150
+global_step200

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71943a7534a603fc1073a728ef828fea525cdf5f25bf2fd0efc0240e6f46ebfc
+oid sha256:fe71a984f3dec9f68d5e0c8d287b709dc94679e36c2f73fcd4bb577f118dc56b
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63b213587c483eed36cb75309049fa83568935186952fbec8cb20c41657ce583
+oid sha256:073d3d50c553c506414b06b3236a0e47ab676db77072aa4ada6dbd9ccae3efe8
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a070f5332db568fae86334a08fc1d346399db4a28d7560e846aae021f5cf8fe0
+oid sha256:e4448dc49072e0161b26ca29cf232331ae40e44f83c87e97c7b098177ab3622b
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ce84bc4f574a8a3540d6a08d280ebfeea47cd3c1b20a8bcc24e2a3baed0176
+oid sha256:bad727f18a1ed5b11da2bd5fee112f9da1775401ade913bb7443084b78e34672
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b8ced64010d7c63b9599d6610f10182005fca711e469c3a69c02f6738b2037
+oid sha256:267a8256d64aed80d8aed25b49adf5bf4d92086abb3964c902d2e45f4a76d74e
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.7854999899864197,
+  "best_metric": 0.7729406356811523,
   "best_model_checkpoint": null,
-  "epoch": 0.14696876913655849,
+  "epoch": 0.19595835884874463,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -242,6 +242,84 @@
       "eval_samples_per_second": 130.904,
       "eval_steps_per_second": 16.371,
       "step": 150
+    },
+    {
+      "epoch": 0.1518677281077771,
+      "grad_norm": 0.2067604809999466,
+      "learning_rate": 0.00011076407880230177,
+      "loss": 0.7802,
+      "step": 155
+    },
+    {
+      "epoch": 0.15676668707899571,
+      "grad_norm": 0.23229490220546722,
+      "learning_rate": 0.00011075764704038947,
+      "loss": 0.7935,
+      "step": 160
+    },
+    {
+      "epoch": 0.16166564605021433,
+      "grad_norm": 0.26088929176330566,
+      "learning_rate": 0.00011075064637901441,
+      "loss": 0.7996,
+      "step": 165
+    },
+    {
+      "epoch": 0.16656460502143294,
+      "grad_norm": 0.23547124862670898,
+      "learning_rate": 0.00011074307689011918,
+      "loss": 0.8011,
+      "step": 170
+    },
+    {
+      "epoch": 0.17146356399265156,
+      "grad_norm": 0.24739272892475128,
+      "learning_rate": 0.00011073493865149204,
+      "loss": 0.7854,
+      "step": 175
+    },
+    {
+      "epoch": 0.17636252296387017,
+      "grad_norm": 0.222539022564888,
+      "learning_rate": 0.00011072623174676594,
+      "loss": 0.7962,
+      "step": 180
+    },
+    {
+      "epoch": 0.1812614819350888,
+      "grad_norm": 0.2204458862543106,
+      "learning_rate": 0.00011071695626541782,
+      "loss": 0.7958,
+      "step": 185
+    },
+    {
+      "epoch": 0.1861604409063074,
+      "grad_norm": 0.2629190683364868,
+      "learning_rate": 0.00011070711230276759,
+      "loss": 0.7779,
+      "step": 190
+    },
+    {
+      "epoch": 0.19105939987752601,
+      "grad_norm": 0.22338400781154633,
+      "learning_rate": 0.00011069669995997721,
+      "loss": 0.7972,
+      "step": 195
+    },
+    {
+      "epoch": 0.19595835884874463,
+      "grad_norm": 0.20890545845031738,
+      "learning_rate": 0.00011068571934404962,
+      "loss": 0.7769,
+      "step": 200
+    },
+    {
+      "epoch": 0.19595835884874463,
+      "eval_loss": 0.7729406356811523,
+      "eval_runtime": 15.0332,
+      "eval_samples_per_second": 130.311,
+      "eval_steps_per_second": 16.297,
+      "step": 200
     }
   ],
   "logging_steps": 5,
@@ -270,7 +348,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.859423388316467e+16,
+  "total_flos": 1.0404528961408205e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null