Training in progress, epoch 1, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ba24fbd78f41f87732df853af0a794a16da513562ad1a71af5f966baa039c4a
+oid sha256:167731ecb29f1009da193f68282d52ab930805b2ec25f381ffb028e41e7774a9
 size 98088784

last-checkpoint/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29a046dd4187e32034d8ffc5eaff22aec1428a5ddfa3e502bd717701b32ebf3e
+size 73939813

last-checkpoint/global_step1400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ff5a68cfc6bd48311101a125f187c857e1e8a89dfaeeb445a14bc71e93e175
+size 73939813

last-checkpoint/global_step1400/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a634c4a56180bca55914dd50453cabfaa51496a5497da7680da694be8dbb004
+size 73939877

last-checkpoint/global_step1400/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601f68ff1943d3a0b38b8d025d6813ff5769c0d0166b37e3a5fd6b887db159a0
+size 73939877

last-checkpoint/global_step1400/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8973ce3d87ce8fd9c37ca4539134a46c59820edeee7caa68c02a5af950ef5303
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step1350
+global_step1400

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa79ae81c764ce09a49eada23a3a13260a93f15acecf71978520994c53a6fe5
+oid sha256:66ecca26d3d57f3aa8de8c8752967d11df785769dded82c892c68155340f1cef
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da6a59295b3b6c4b6391a83f1798476aacb53866db90dbc1917c1a7e5da14ffe
+oid sha256:8f7c0886f14abd4d317af500f3461bca4e4ce8168823dadd261e5d96bb678592
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0faa1d73e0c71ce74533d82a1c768084de01b5180442f96fdf898f6cb86452c4
+oid sha256:ed288a32471998bc0e438fc0eb0db6765002d3bc4943f31d6e9324b1369f4ae3
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c51d1564bc85d65cee1a279631370f3bd797adc024486c9cf28688e3908be4c
+oid sha256:c4f0b48724660b89ddddb538b164dd4f3670242789a9907278e96733bbd9d8f1
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e027f975de877ececa955f9ce9f43586096f7e3b7c1ba28980929c75ca98a5bf
+oid sha256:bd3531245cd9f210f9f9029c53dc69b2706a0814b9ab61730382b6d4ad3b3bed
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6760671138763428,
+  "best_metric": 0.6735198497772217,
   "best_model_checkpoint": null,
-  "epoch": 1.3233312921004288,
+  "epoch": 1.3723208818126147,
   "eval_steps": 50,
-  "global_step": 1350,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2114,6 +2114,84 @@
       "eval_samples_per_second": 126.318,
       "eval_steps_per_second": 15.798,
       "step": 1350
+    },
+    {
+      "epoch": 1.3282302510716473,
+      "grad_norm": 0.19919976592063904,
+      "learning_rate": 9.383632005567528e-05,
+      "loss": 0.6887,
+      "step": 1355
+    },
+    {
+      "epoch": 1.3331292100428658,
+      "grad_norm": 0.19178372621536255,
+      "learning_rate": 9.370823339698302e-05,
+      "loss": 0.6862,
+      "step": 1360
+    },
+    {
+      "epoch": 1.3380281690140845,
+      "grad_norm": 0.24898383021354675,
+      "learning_rate": 9.357975304793234e-05,
+      "loss": 0.6956,
+      "step": 1365
+    },
+    {
+      "epoch": 1.3429271279853032,
+      "grad_norm": 0.2015768438577652,
+      "learning_rate": 9.345088032885762e-05,
+      "loss": 0.6818,
+      "step": 1370
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 0.2135515958070755,
+      "learning_rate": 9.332161656412545e-05,
+      "loss": 0.7147,
+      "step": 1375
+    },
+    {
+      "epoch": 1.3527250459277402,
+      "grad_norm": 0.22946955263614655,
+      "learning_rate": 9.319196308212099e-05,
+      "loss": 0.7069,
+      "step": 1380
+    },
+    {
+      "epoch": 1.357624004898959,
+      "grad_norm": 0.21383248269557953,
+      "learning_rate": 9.306192121523441e-05,
+      "loss": 0.6876,
+      "step": 1385
+    },
+    {
+      "epoch": 1.3625229638701777,
+      "grad_norm": 0.2196836769580841,
+      "learning_rate": 9.293149229984704e-05,
+      "loss": 0.7183,
+      "step": 1390
+    },
+    {
+      "epoch": 1.3674219228413962,
+      "grad_norm": 0.207967147231102,
+      "learning_rate": 9.280067767631785e-05,
+      "loss": 0.6937,
+      "step": 1395
+    },
+    {
+      "epoch": 1.3723208818126147,
+      "grad_norm": 0.21403300762176514,
+      "learning_rate": 9.266947868896943e-05,
+      "loss": 0.6952,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3723208818126147,
+      "eval_loss": 0.6735198497772217,
+      "eval_runtime": 15.564,
+      "eval_samples_per_second": 125.867,
+      "eval_steps_per_second": 15.741,
+      "step": 1400
     }
   ],
   "logging_steps": 5,
@@ -2142,7 +2220,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.965313910089974e+17,
+  "total_flos": 7.222224350169006e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null