Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87d361f1f20ce9468d8769ea62547fa2f00d10b4294e98d9f7ea0fec07272575
+oid sha256:9d0de5afa78ac1a851770e965747119dc908a8573a1881c1b62ef94e117361b7
 size 98088784

last-checkpoint/global_step2400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eca27fd9fb0a5ccfb181005311c816501232bcd490ae20b9c76a559af8d89d4
+size 73939813

last-checkpoint/global_step2400/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:bf18680764523fdc9869bfbacc89915f6eb82f3cea3955743bac52e752b8b6e0
+size 73939813

last-checkpoint/global_step2400/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:648c9462de29cb85b3bf682d3337bdf29b99395a61a8bfdfd4879e7471aa2a97
+size 73939877

last-checkpoint/global_step2400/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:a9beacb3cd36204c636a6f00bd5d83f70a48f4039bd1f687bb26d08b6da09724
+size 73939877

last-checkpoint/global_step2400/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:275f489d3cb498bdc277a99a7e8602204f234bce5847aad1592e8c22a242b6be
+size 564993061

last-checkpoint/latest

@@ -1 +1 @@
-global_step2350
+global_step2400

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2628c730b225bca8e769fb7d77bc63f6ab1bf00c6de3e0718b778b68f3ccf4
+oid sha256:da2a61b9255c6e0e14b465f319d25cae5a6feda6a13a002c1330320903ec32ad
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2854841ad4985b4bea7ef0b85dd207340a6e1c4a794b3c5616cf9329310c6cb9
+oid sha256:9357e3a5c977cdb840cf995ddd764b47d01408206def677d501f66d896c6ec5e
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb425516dc42e49f548214607eb38a06346c10fe44134f756d1a1b16e904158a
+oid sha256:26225e55dcbf38d84553146ca4ec5fd80f656353ee4bcccad7e7d71f62e26286
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3aa542567ede48437c38b77556047950204e99fde68d0fb18040ac8e6d60b8
+oid sha256:47317384c9b80cc6d594282a948dcef2ef0674cecf18085345417f0b6c4d5255
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb38cc87a12a48888b80575c9f941f93276629c644ddd80ad58596b1ccb4208d
+oid sha256:d64a5f5783a1fbfde4e4b1350176304a7071802b5982d96b34edf354307118ae
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.6389577388763428,
+  "best_metric": 0.6379070281982422,
   "best_model_checkpoint": null,
-  "epoch": 2.3037354562155543,
+  "epoch": 2.3527250459277402,
   "eval_steps": 50,
-  "global_step": 2350,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3674,6 +3674,84 @@
       "eval_samples_per_second": 126.24,
       "eval_steps_per_second": 15.788,
       "step": 2350
+    },
+    {
+      "epoch": 2.3086344151867726,
+      "grad_norm": 0.21627400815486908,
+      "learning_rate": 6.234192926986104e-05,
+      "loss": 0.6771,
+      "step": 2355
+    },
+    {
+      "epoch": 2.3135333741579913,
+      "grad_norm": 0.21867620944976807,
+      "learning_rate": 6.216570246709919e-05,
+      "loss": 0.6794,
+      "step": 2360
+    },
+    {
+      "epoch": 2.31843233312921,
+      "grad_norm": 0.22947458922863007,
+      "learning_rate": 6.19894061222874e-05,
+      "loss": 0.6557,
+      "step": 2365
+    },
+    {
+      "epoch": 2.3233312921004288,
+      "grad_norm": 0.22656455636024475,
+      "learning_rate": 6.181304204714342e-05,
+      "loss": 0.6472,
+      "step": 2370
+    },
+    {
+      "epoch": 2.3282302510716475,
+      "grad_norm": 0.24354885518550873,
+      "learning_rate": 6.1636612054081e-05,
+      "loss": 0.6578,
+      "step": 2375
+    },
+    {
+      "epoch": 2.3331292100428658,
+      "grad_norm": 0.22579948604106903,
+      "learning_rate": 6.146011795619128e-05,
+      "loss": 0.6519,
+      "step": 2380
+    },
+    {
+      "epoch": 2.3380281690140845,
+      "grad_norm": 0.20197154581546783,
+      "learning_rate": 6.128356156722419e-05,
+      "loss": 0.672,
+      "step": 2385
+    },
+    {
+      "epoch": 2.3429271279853032,
+      "grad_norm": 0.2026195526123047,
+      "learning_rate": 6.110694470156979e-05,
+      "loss": 0.6996,
+      "step": 2390
+    },
+    {
+      "epoch": 2.3478260869565215,
+      "grad_norm": 0.21798843145370483,
+      "learning_rate": 6.093026917423967e-05,
+      "loss": 0.6664,
+      "step": 2395
+    },
+    {
+      "epoch": 2.3527250459277402,
+      "grad_norm": 0.20497962832450867,
+      "learning_rate": 6.075353680084818e-05,
+      "loss": 0.6718,
+      "step": 2400
+    },
+    {
+      "epoch": 2.3527250459277402,
+      "eval_loss": 0.6379070281982422,
+      "eval_runtime": 15.5692,
+      "eval_samples_per_second": 125.825,
+      "eval_steps_per_second": 15.736,
+      "step": 2400
     }
   ],
   "logging_steps": 5,
@@ -3702,7 +3780,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2107217105636557e+18,
+  "total_flos": 1.23700887616802e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null