Training in progress, epoch 1, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbd7e7ee0e0b0d24778ae4ae26100b0a8fb2df96c0c8e46068a21bb252a4bf39
+oid sha256:a0b2192cab039402b759c7755739934206cf2585c7ded8de3eba8e8a4711f0f2
 size 98088784

last-checkpoint/global_step1600/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e6242c13ae98b8a5cbe60e5ad651c403bb13deedea6b758ac3fc066fc1a3ac
+size 73939813

last-checkpoint/global_step1600/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ed76c8aaa1ef74b40fbc859d853a5c8344f37e789b087826352ff27c85296a
+size 73939813

last-checkpoint/global_step1600/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:384d53dcec29199c1a7bf744018c71f65b4a798b58a2526e0a6f485dc25b1cad
+size 73939877

last-checkpoint/global_step1600/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:e006e5a3030d4fc513e5c423de939f5b9cd0faa645e0b0ad363d85078ceccd8e
+size 73939877

last-checkpoint/global_step1600/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11bbc3b21a3d45ce24346133fd20140bab87f069916c01102d188f1090ea0202
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step1550
+global_step1600

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e01ef876a968a28df370a06abf6d57c6d373bd832789aaf63d56fde5afbe7bb
+oid sha256:1eedf98ea9975d3d0f462291ea7b85b1da5289375a42dca5aaa06c6d74ce34c5
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e8b5a3d8a67eeb06d474c91493fbd7ff584a0b5183fd544d54b0c6eb1c4e56c
+oid sha256:c1d8118304cff88474c86198c7f5aa76463f040ece3bc21b07aecbb56d4fa64a
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c1801ecd5d4bb9dd5fe34a6df0b80f63650a26836f380f43dd909361d68fe1
+oid sha256:429e5f6db3d40572a6c2433c9bdbbba576389574bcdd6f230c7b20ea60fcad6b
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca02c741884e18e1696ec0f5091b962de1adf48b6c8c872b9fe8bad0a58b156
+oid sha256:25916e2cde20cc021d3d06b16632aaf89d5216f10390eef1707ef1a019a03407
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:623d7e2a01cfe6bc8edd920eeeb1368be0061931f43bba9f8429c60a7e24e4e0
+oid sha256:5aa753350ab43e2a824d8e89dd96b9a3ddede15e688d15c87d248607ff08488a
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6680008769035339,
+  "best_metric": 0.6650952696800232,
   "best_model_checkpoint": null,
-  "epoch": 1.5192896509491733,
+  "epoch": 1.5682792406613595,
   "eval_steps": 50,
-  "global_step": 1550,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2426,6 +2426,84 @@
       "eval_samples_per_second": 126.077,
       "eval_steps_per_second": 15.768,
       "step": 1550
+    },
+    {
+      "epoch": 1.524188609920392,
+      "grad_norm": 0.20915450155735016,
+      "learning_rate": 8.841917952432193e-05,
+      "loss": 0.7048,
+      "step": 1555
+    },
+    {
+      "epoch": 1.5290875688916106,
+      "grad_norm": 0.21618790924549103,
+      "learning_rate": 8.827641367989242e-05,
+      "loss": 0.6895,
+      "step": 1560
+    },
+    {
+      "epoch": 1.533986527862829,
+      "grad_norm": 0.20739570260047913,
+      "learning_rate": 8.813330996545632e-05,
+      "loss": 0.712,
+      "step": 1565
+    },
+    {
+      "epoch": 1.5388854868340478,
+      "grad_norm": 0.2209644615650177,
+      "learning_rate": 8.798986985162568e-05,
+      "loss": 0.6987,
+      "step": 1570
+    },
+    {
+      "epoch": 1.5437844458052665,
+      "grad_norm": 0.20145706832408905,
+      "learning_rate": 8.784609481246963e-05,
+      "loss": 0.71,
+      "step": 1575
+    },
+    {
+      "epoch": 1.548683404776485,
+      "grad_norm": 0.20716360211372375,
+      "learning_rate": 8.770198632549912e-05,
+      "loss": 0.6984,
+      "step": 1580
+    },
+    {
+      "epoch": 1.5535823637477035,
+      "grad_norm": 0.1935468167066574,
+      "learning_rate": 8.755754587165184e-05,
+      "loss": 0.701,
+      "step": 1585
+    },
+    {
+      "epoch": 1.5584813227189223,
+      "grad_norm": 0.19698968529701233,
+      "learning_rate": 8.741277493527693e-05,
+      "loss": 0.6829,
+      "step": 1590
+    },
+    {
+      "epoch": 1.563380281690141,
+      "grad_norm": 0.20820119976997375,
+      "learning_rate": 8.726767500411974e-05,
+      "loss": 0.6963,
+      "step": 1595
+    },
+    {
+      "epoch": 1.5682792406613595,
+      "grad_norm": 0.18384264409542084,
+      "learning_rate": 8.712224756930659e-05,
+      "loss": 0.7072,
+      "step": 1600
+    },
+    {
+      "epoch": 1.5682792406613595,
+      "eval_loss": 0.6650952696800232,
+      "eval_runtime": 15.609,
+      "eval_samples_per_second": 125.505,
+      "eval_steps_per_second": 15.696,
+      "step": 1600
     }
   ],
   "logging_steps": 5,
@@ -2454,7 +2532,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.99411319630463e+17,
+  "total_flos": 8.252213790611866e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null