Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "up_proj",
-    "k_proj",
-    "down_proj",
     "v_proj",
+    "up_proj",
     "o_proj",
-    "gate_proj"
+    "gate_proj",
+    "k_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c47cb6892419d600696e2055d6e60537852d33200fb6cec8e14d31a9146d072
+oid sha256:d197a290c8d110cb7014b8bfd5115dc80fb0be310fe74172fb608acc8e387ca6
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:304e3bf86ce5020271a09408cb3889312254d13fed75bb5da2f32bef11df815f
+oid sha256:395a8f52ec78b6d75492b0e57f9645a4c678f6ada929602e525129725fdfc6f3
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:6e4a3ee778160f42a22e93367025f5b4d76e7fc51b428625824d02549c0d97d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0047711346354554944,
-  "eval_steps": 2,
-  "global_step": 2,
+  "epoch": 0.031012375130460713,
+  "eval_steps": 13,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0023855673177277472,
-      "grad_norm": 1.2481120824813843,
+      "grad_norm": 1.3246102333068848,
       "learning_rate": 1e-05,
       "loss": 0.9265,
       "step": 1
@@ -18,32 +18,109 @@
     {
       "epoch": 0.0023855673177277472,
       "eval_loss": 0.9870346188545227,
-      "eval_runtime": 65.0919,
-      "eval_samples_per_second": 10.846,
-      "eval_steps_per_second": 5.423,
+      "eval_runtime": 65.1117,
+      "eval_samples_per_second": 10.843,
+      "eval_steps_per_second": 5.421,
       "step": 1
     },
     {
       "epoch": 0.0047711346354554944,
-      "grad_norm": 1.427655577659607,
+      "grad_norm": 1.5241637229919434,
       "learning_rate": 2e-05,
       "loss": 1.0298,
       "step": 2
     },
     {
-      "epoch": 0.0047711346354554944,
-      "eval_loss": 0.9387862086296082,
-      "eval_runtime": 16.6543,
-      "eval_samples_per_second": 42.392,
-      "eval_steps_per_second": 21.196,
-      "step": 2
+      "epoch": 0.007156701953183241,
+      "grad_norm": 1.3183329105377197,
+      "learning_rate": 3e-05,
+      "loss": 0.9629,
+      "step": 3
+    },
+    {
+      "epoch": 0.009542269270910989,
+      "grad_norm": 1.3316704034805298,
+      "learning_rate": 4e-05,
+      "loss": 0.9491,
+      "step": 4
+    },
+    {
+      "epoch": 0.011927836588638736,
+      "grad_norm": 1.2836781740188599,
+      "learning_rate": 5e-05,
+      "loss": 0.8294,
+      "step": 5
+    },
+    {
+      "epoch": 0.014313403906366482,
+      "grad_norm": 1.3446112871170044,
+      "learning_rate": 6e-05,
+      "loss": 0.7596,
+      "step": 6
+    },
+    {
+      "epoch": 0.01669897122409423,
+      "grad_norm": 1.3533251285552979,
+      "learning_rate": 7e-05,
+      "loss": 0.8652,
+      "step": 7
+    },
+    {
+      "epoch": 0.019084538541821978,
+      "grad_norm": 1.2886685132980347,
+      "learning_rate": 8e-05,
+      "loss": 0.6794,
+      "step": 8
+    },
+    {
+      "epoch": 0.021470105859549723,
+      "grad_norm": 1.0436530113220215,
+      "learning_rate": 9e-05,
+      "loss": 0.5633,
+      "step": 9
+    },
+    {
+      "epoch": 0.02385567317727747,
+      "grad_norm": 0.8520669937133789,
+      "learning_rate": 0.0001,
+      "loss": 0.4955,
+      "step": 10
+    },
+    {
+      "epoch": 0.02624124049500522,
+      "grad_norm": 0.7037628889083862,
+      "learning_rate": 9.98458666866564e-05,
+      "loss": 0.3973,
+      "step": 11
+    },
+    {
+      "epoch": 0.028626807812732965,
+      "grad_norm": 0.8181518912315369,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 0.4359,
+      "step": 12
+    },
+    {
+      "epoch": 0.031012375130460713,
+      "grad_norm": 0.6722888946533203,
+      "learning_rate": 9.861849601988383e-05,
+      "loss": 0.3231,
+      "step": 13
+    },
+    {
+      "epoch": 0.031012375130460713,
+      "eval_loss": 0.303219199180603,
+      "eval_runtime": 16.6267,
+      "eval_samples_per_second": 42.462,
+      "eval_steps_per_second": 21.231,
+      "step": 13
     }
   ],
   "logging_steps": 1,
-  "max_steps": 5,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 2,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -56,7 +133,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1318258338693120.0,
+  "total_flos": 8568679201505280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e263d391be8f592d64c6f477c3e14ccc7c583c050e5bbadc9320af574c2d1c3
+oid sha256:31b5cdd3cd707bf07eb2bb55c3a7762a30f419ba7acabac68f8e2c545a57fb8b
 size 6776