Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95368131cd8359671ea43b4a22491aa71c11c57d28f43174c3cb80e62ebada9c
+oid sha256:4faae999aae7bdb005e759f5800196dad8c366321f5757ffb0cd810595ad0722
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f18f13f0705177994530d1dd618c0d7b5efbd51f3e48d857ccef984d6b20871
+oid sha256:2de6ec90481b17fdf0dbb66af6a33a218beab40180fd7766e682f67587ccf105
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3afb0296dcc09baa2a732110722104ee83350cd7e8d7c060b994344f5c6a1a5
+oid sha256:4f87b4e2959c3797be663a45d01659738f60369c9bf34bc2324a8a07e37c7d7e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010223139683475867,
+  "epoch": 0.020446279366951734,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 2.708,
       "eval_steps_per_second": 1.354,
       "step": 13
+    },
+    {
+      "epoch": 0.011009535043743243,
+      "grad_norm": 1.8393322229385376,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.8994,
+      "step": 14
+    },
+    {
+      "epoch": 0.011795930404010616,
+      "grad_norm": 2.288557529449463,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.964,
+      "step": 15
+    },
+    {
+      "epoch": 0.01258232576427799,
+      "grad_norm": 2.239872455596924,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.8643,
+      "step": 16
+    },
+    {
+      "epoch": 0.013368721124545365,
+      "grad_norm": 2.4298009872436523,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 0.9466,
+      "step": 17
+    },
+    {
+      "epoch": 0.01415511648481274,
+      "grad_norm": 3.0432651042938232,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.0756,
+      "step": 18
+    },
+    {
+      "epoch": 0.014941511845080115,
+      "grad_norm": 1.3065857887268066,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 0.6739,
+      "step": 19
+    },
+    {
+      "epoch": 0.01572790720534749,
+      "grad_norm": 2.0720527172088623,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8697,
+      "step": 20
+    },
+    {
+      "epoch": 0.016514302565614862,
+      "grad_norm": 1.8250558376312256,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.7318,
+      "step": 21
+    },
+    {
+      "epoch": 0.017300697925882236,
+      "grad_norm": 2.166428565979004,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.7315,
+      "step": 22
+    },
+    {
+      "epoch": 0.018087093286149613,
+      "grad_norm": 2.2534689903259277,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 0.9042,
+      "step": 23
+    },
+    {
+      "epoch": 0.018873488646416987,
+      "grad_norm": 1.4026483297348022,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.7183,
+      "step": 24
+    },
+    {
+      "epoch": 0.01965988400668436,
+      "grad_norm": 1.6705015897750854,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.6787,
+      "step": 25
+    },
+    {
+      "epoch": 0.020446279366951734,
+      "grad_norm": 2.1395044326782227,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.9407,
+      "step": 26
+    },
+    {
+      "epoch": 0.020446279366951734,
+      "eval_loss": 0.8785327672958374,
+      "eval_runtime": 781.2326,
+      "eval_samples_per_second": 2.742,
+      "eval_steps_per_second": 1.371,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.975701360043622e+16,
+  "total_flos": 1.5951402720087245e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null